Upload folder using huggingface_hub
Browse files- .gitattributes +6 -0
 - .summary/0/events.out.tfevents.1717635033.4a1f19113fa6 +3 -0
 - .summary/0/events.out.tfevents.1717700366.c11948e043d9 +3 -0
 - .summary/0/events.out.tfevents.1717702446.c11948e043d9 +3 -0
 - .summary/0/events.out.tfevents.1717708092.c11948e043d9 +3 -0
 - .summary/0/events.out.tfevents.1717708590.c11948e043d9 +3 -0
 - .summary/0/events.out.tfevents.1717710273.c11948e043d9 +3 -0
 - .summary/0/events.out.tfevents.1717711462.c11948e043d9 +3 -0
 - .summary/0/events.out.tfevents.1717717783.c11948e043d9 +3 -0
 - README.md +42 -0
 - a100_100x100.mp4 +3 -0
 - a20_40x40.mp4 +3 -0
 - a20_b4_40x40.mp4 +3 -0
 - a20_r4_40x40.mp4 +3 -0
 - a5_25x25.mp4 +0 -0
 - checkpoint_p0/best_000870321_14259339264_reward_0.370.pth +3 -0
 - checkpoint_p0/checkpoint_000971348_15914565632.pth +3 -0
 - checkpoint_p0/checkpoint_000971574_15918268416.pth +3 -0
 - config.json +161 -0
 - git.diff +0 -0
 - replay.mp4 +3 -0
 - sf_log.txt +3 -0
 
    	
        .gitattributes
    CHANGED
    
    | 
         @@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text 
     | 
|
| 33 | 
         
             
            *.zip filter=lfs diff=lfs merge=lfs -text
         
     | 
| 34 | 
         
             
            *.zst filter=lfs diff=lfs merge=lfs -text
         
     | 
| 35 | 
         
             
            *tfevents* filter=lfs diff=lfs merge=lfs -text
         
     | 
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 33 | 
         
             
            *.zip filter=lfs diff=lfs merge=lfs -text
         
     | 
| 34 | 
         
             
            *.zst filter=lfs diff=lfs merge=lfs -text
         
     | 
| 35 | 
         
             
            *tfevents* filter=lfs diff=lfs merge=lfs -text
         
     | 
| 36 | 
         
            +
            a100_100x100.mp4 filter=lfs diff=lfs merge=lfs -text
         
     | 
| 37 | 
         
            +
            a20_40x40.mp4 filter=lfs diff=lfs merge=lfs -text
         
     | 
| 38 | 
         
            +
            a20_b4_40x40.mp4 filter=lfs diff=lfs merge=lfs -text
         
     | 
| 39 | 
         
            +
            a20_r4_40x40.mp4 filter=lfs diff=lfs merge=lfs -text
         
     | 
| 40 | 
         
            +
            replay.mp4 filter=lfs diff=lfs merge=lfs -text
         
     | 
| 41 | 
         
            +
            sf_log.txt filter=lfs diff=lfs merge=lfs -text
         
     | 
    	
        .summary/0/events.out.tfevents.1717635033.4a1f19113fa6
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:ee45b727ef73050650719d6370bb442ed773c108c5efa37345fd1a1195f4cae0
         
     | 
| 3 | 
         
            +
            size 2433024
         
     | 
    	
        .summary/0/events.out.tfevents.1717700366.c11948e043d9
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:1cf6cafad438ea9510a7e6f67df1fb9eb1ff981d02fe2e588bfa5af45242fe1e
         
     | 
| 3 | 
         
            +
            size 861005
         
     | 
    	
        .summary/0/events.out.tfevents.1717702446.c11948e043d9
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:8603f0d9093699a29995f4ae331c45933b2d8ebc4a2f416da7a29df9b07ab809
         
     | 
| 3 | 
         
            +
            size 4371047
         
     | 
    	
        .summary/0/events.out.tfevents.1717708092.c11948e043d9
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:ddeda34714771693362020b4a67d629000665abf6347166f03b8b5b7d43765c3
         
     | 
| 3 | 
         
            +
            size 40
         
     | 
    	
        .summary/0/events.out.tfevents.1717708590.c11948e043d9
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:d5918fd3155796d72554d67c6aa10370132f2c23daf769ed383de0d09a63f693
         
     | 
| 3 | 
         
            +
            size 1183336
         
     | 
    	
        .summary/0/events.out.tfevents.1717710273.c11948e043d9
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:f9de5828b5e679da8fd5921ac0b5419e928d328aabb81b0e0d59e7eac9370a41
         
     | 
| 3 | 
         
            +
            size 823211
         
     | 
    	
        .summary/0/events.out.tfevents.1717711462.c11948e043d9
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:8f8af146e539d3252a7c61c5decc896ba431958591cb8755355b2d90419f9966
         
     | 
| 3 | 
         
            +
            size 4548736
         
     | 
    	
        .summary/0/events.out.tfevents.1717717783.c11948e043d9
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:dd6de054b926c2457045c682a95d24d8fc6385270ebc950aa3b2ff65d547f3d8
         
     | 
| 3 | 
         
            +
            size 218032052
         
     | 
    	
        README.md
    ADDED
    
    | 
         @@ -0,0 +1,42 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            ---
         
     | 
| 2 | 
         
            +
            library_name: sample-factory
         
     | 
| 3 | 
         
            +
            tags:
         
     | 
| 4 | 
         
            +
            - deep-reinforcement-learning
         
     | 
| 5 | 
         
            +
            - reinforcement-learning
         
     | 
| 6 | 
         
            +
            - sample-factory
         
     | 
| 7 | 
         
            +
            ---
         
     | 
| 8 | 
         
            +
             
     | 
| 9 | 
         
            +
            A(n) **APPO** model trained on the **GDY-MettaGrid** environment.
         
     | 
| 10 | 
         
            +
             
     | 
| 11 | 
         
            +
            This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
         
     | 
| 12 | 
         
            +
            Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
         
     | 
| 13 | 
         
            +
             
     | 
| 14 | 
         
            +
             
     | 
| 15 | 
         
            +
            ## Downloading the model
         
     | 
| 16 | 
         
            +
             
     | 
| 17 | 
         
            +
            After installing Sample-Factory, download the model with:
         
     | 
| 18 | 
         
            +
            ```
         
     | 
| 19 | 
         
            +
            python -m sample_factory.huggingface.load_from_hub -r metta-ai/baseline.v0.2.2
         
     | 
| 20 | 
         
            +
            ```
         
     | 
| 21 | 
         
            +
             
     | 
| 22 | 
         
            +
                
         
     | 
| 23 | 
         
            +
            ## Using the model
         
     | 
| 24 | 
         
            +
             
     | 
| 25 | 
         
            +
            To run the model after download, use the `enjoy` script corresponding to this environment:
         
     | 
| 26 | 
         
            +
            ```
         
     | 
| 27 | 
         
            +
            python -m <path.to.enjoy.module> --algo=APPO --env=GDY-MettaGrid --train_dir=./train_dir --experiment=baseline.v0.2.2
         
     | 
| 28 | 
         
            +
            ```
         
     | 
| 29 | 
         
            +
             
     | 
| 30 | 
         
            +
             
     | 
| 31 | 
         
            +
            You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
         
     | 
| 32 | 
         
            +
            See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
         
     | 
| 33 | 
         
            +
                
         
     | 
| 34 | 
         
            +
            ## Training with this model
         
     | 
| 35 | 
         
            +
             
     | 
| 36 | 
         
            +
            To continue training with this model, use the `train` script corresponding to this environment:
         
     | 
| 37 | 
         
            +
            ```
         
     | 
| 38 | 
         
            +
            python -m <path.to.train.module> --algo=APPO --env=GDY-MettaGrid --train_dir=./train_dir --experiment=baseline.v0.2.2 --restart_behavior=resume --train_for_env_steps=10000000000
         
     | 
| 39 | 
         
            +
            ```
         
     | 
| 40 | 
         
            +
             
     | 
| 41 | 
         
            +
            Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
         
     | 
| 42 | 
         
            +
                
         
     | 
    	
        a100_100x100.mp4
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:dea77db32fda2241d5541d48313bdedb572bcbb994004f10b4b723e205e2e203
         
     | 
| 3 | 
         
            +
            size 9661669
         
     | 
    	
        a20_40x40.mp4
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:7fd1f4b5380956f834d3df0c89e055f5a3584825d0a85f6cfb2c673ff4c18db8
         
     | 
| 3 | 
         
            +
            size 1949240
         
     | 
    	
        a20_b4_40x40.mp4
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:0ac08b8d66f5475591d97b5c754cbedace2be3b94ec148eabbe08a21013ba57f
         
     | 
| 3 | 
         
            +
            size 1271422
         
     | 
    	
        a20_r4_40x40.mp4
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:8f43b88b0a42e372ea1291e4a67c5a030444c0044118d6ff15e7dbbe04d4342a
         
     | 
| 3 | 
         
            +
            size 2273096
         
     | 
    	
        a5_25x25.mp4
    ADDED
    
    | 
         Binary file (892 kB). View file 
     | 
| 
         | 
    	
        checkpoint_p0/best_000870321_14259339264_reward_0.370.pth
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:f5e1a05f7aaf6d4eda8331fd9a9742e5a1e223ed6ba2118cf6f3eb7630b90360
         
     | 
| 3 | 
         
            +
            size 38973114
         
     | 
    	
        checkpoint_p0/checkpoint_000971348_15914565632.pth
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:342f8d8f91bd2e597164eb4690a493a057fe1e8c079f38f584e061e04f9b37ab
         
     | 
| 3 | 
         
            +
            size 38974422
         
     | 
    	
        checkpoint_p0/checkpoint_000971574_15918268416.pth
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:2615ca4ce26eb958d7a1258895fe25193e4d539a8e91d769af0c6a9e8ecfe89a
         
     | 
| 3 | 
         
            +
            size 38974422
         
     | 
    	
        config.json
    ADDED
    
    | 
         @@ -0,0 +1,161 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "help": false,
         
     | 
| 3 | 
         
            +
              "algo": "APPO",
         
     | 
| 4 | 
         
            +
              "env": "GDY-MettaGrid",
         
     | 
| 5 | 
         
            +
              "experiment": "p2.metta.4",
         
     | 
| 6 | 
         
            +
              "train_dir": "/workspace/metta/train_dir",
         
     | 
| 7 | 
         
            +
              "restart_behavior": "resume",
         
     | 
| 8 | 
         
            +
              "device": "gpu",
         
     | 
| 9 | 
         
            +
              "seed": 0,
         
     | 
| 10 | 
         
            +
              "num_policies": 1,
         
     | 
| 11 | 
         
            +
              "async_rl": true,
         
     | 
| 12 | 
         
            +
              "serial_mode": false,
         
     | 
| 13 | 
         
            +
              "batched_sampling": false,
         
     | 
| 14 | 
         
            +
              "num_batches_to_accumulate": 2,
         
     | 
| 15 | 
         
            +
              "worker_num_splits": 2,
         
     | 
| 16 | 
         
            +
              "policy_workers_per_policy": 1,
         
     | 
| 17 | 
         
            +
              "max_policy_lag": 50,
         
     | 
| 18 | 
         
            +
              "num_workers": 32,
         
     | 
| 19 | 
         
            +
              "num_envs_per_worker": 2,
         
     | 
| 20 | 
         
            +
              "batch_size": 16384,
         
     | 
| 21 | 
         
            +
              "num_batches_per_epoch": 1,
         
     | 
| 22 | 
         
            +
              "num_epochs": 1,
         
     | 
| 23 | 
         
            +
              "rollout": 256,
         
     | 
| 24 | 
         
            +
              "recurrence": 256,
         
     | 
| 25 | 
         
            +
              "shuffle_minibatches": false,
         
     | 
| 26 | 
         
            +
              "gamma": 0.99,
         
     | 
| 27 | 
         
            +
              "reward_scale": 1.0,
         
     | 
| 28 | 
         
            +
              "reward_clip": 1000.0,
         
     | 
| 29 | 
         
            +
              "value_bootstrap": false,
         
     | 
| 30 | 
         
            +
              "normalize_returns": true,
         
     | 
| 31 | 
         
            +
              "exploration_loss_coeff": 0.002,
         
     | 
| 32 | 
         
            +
              "value_loss_coeff": 0.976,
         
     | 
| 33 | 
         
            +
              "kl_loss_coeff": 0.0,
         
     | 
| 34 | 
         
            +
              "aux_loss_coeff": 0.0,
         
     | 
| 35 | 
         
            +
              "exploration_loss": "symmetric_kl",
         
     | 
| 36 | 
         
            +
              "gae_lambda": 0.95,
         
     | 
| 37 | 
         
            +
              "ppo_clip_ratio": 0.1,
         
     | 
| 38 | 
         
            +
              "ppo_clip_value": 1.0,
         
     | 
| 39 | 
         
            +
              "with_vtrace": false,
         
     | 
| 40 | 
         
            +
              "vtrace_rho": 1.0,
         
     | 
| 41 | 
         
            +
              "vtrace_c": 1.0,
         
     | 
| 42 | 
         
            +
              "optimizer": "adam",
         
     | 
| 43 | 
         
            +
              "adam_eps": 1e-06,
         
     | 
| 44 | 
         
            +
              "adam_beta1": 0.9,
         
     | 
| 45 | 
         
            +
              "adam_beta2": 0.999,
         
     | 
| 46 | 
         
            +
              "max_grad_norm": 4.0,
         
     | 
| 47 | 
         
            +
              "learning_rate": 0.0001,
         
     | 
| 48 | 
         
            +
              "lr_schedule": "constant",
         
     | 
| 49 | 
         
            +
              "lr_schedule_kl_threshold": 0.008,
         
     | 
| 50 | 
         
            +
              "lr_adaptive_min": 1e-06,
         
     | 
| 51 | 
         
            +
              "lr_adaptive_max": 0.01,
         
     | 
| 52 | 
         
            +
              "obs_subtract_mean": 0.0,
         
     | 
| 53 | 
         
            +
              "obs_scale": 1.0,
         
     | 
| 54 | 
         
            +
              "normalize_input": false,
         
     | 
| 55 | 
         
            +
              "normalize_input_keys": null,
         
     | 
| 56 | 
         
            +
              "decorrelate_experience_max_seconds": 150,
         
     | 
| 57 | 
         
            +
              "decorrelate_envs_on_one_worker": true,
         
     | 
| 58 | 
         
            +
              "actor_worker_gpus": [],
         
     | 
| 59 | 
         
            +
              "set_workers_cpu_affinity": true,
         
     | 
| 60 | 
         
            +
              "force_envs_single_thread": false,
         
     | 
| 61 | 
         
            +
              "default_niceness": 0,
         
     | 
| 62 | 
         
            +
              "log_to_file": true,
         
     | 
| 63 | 
         
            +
              "experiment_summaries_interval": 10,
         
     | 
| 64 | 
         
            +
              "flush_summaries_interval": 30,
         
     | 
| 65 | 
         
            +
              "stats_avg": 100,
         
     | 
| 66 | 
         
            +
              "summaries_use_frameskip": true,
         
     | 
| 67 | 
         
            +
              "heartbeat_interval": 20,
         
     | 
| 68 | 
         
            +
              "heartbeat_reporting_interval": 180,
         
     | 
| 69 | 
         
            +
              "train_for_env_steps": 9999999999999,
         
     | 
| 70 | 
         
            +
              "train_for_seconds": 10000000000,
         
     | 
| 71 | 
         
            +
              "save_every_sec": 120,
         
     | 
| 72 | 
         
            +
              "keep_checkpoints": 2,
         
     | 
| 73 | 
         
            +
              "load_checkpoint_path": null,
         
     | 
| 74 | 
         
            +
              "init_checkpoint_path": null,
         
     | 
| 75 | 
         
            +
              "load_checkpoint_kind": "latest",
         
     | 
| 76 | 
         
            +
              "save_milestones_sec": -1,
         
     | 
| 77 | 
         
            +
              "save_best_every_sec": 5,
         
     | 
| 78 | 
         
            +
              "save_best_metric": "reward",
         
     | 
| 79 | 
         
            +
              "save_best_after": 100000,
         
     | 
| 80 | 
         
            +
              "benchmark": false,
         
     | 
| 81 | 
         
            +
              "encoder_mlp_layers": [
         
     | 
| 82 | 
         
            +
                512,
         
     | 
| 83 | 
         
            +
                512
         
     | 
| 84 | 
         
            +
              ],
         
     | 
| 85 | 
         
            +
              "encoder_conv_architecture": "convnet_simple",
         
     | 
| 86 | 
         
            +
              "encoder_conv_mlp_layers": [
         
     | 
| 87 | 
         
            +
                512
         
     | 
| 88 | 
         
            +
              ],
         
     | 
| 89 | 
         
            +
              "use_rnn": true,
         
     | 
| 90 | 
         
            +
              "rnn_size": 512,
         
     | 
| 91 | 
         
            +
              "rnn_type": "gru",
         
     | 
| 92 | 
         
            +
              "rnn_num_layers": 1,
         
     | 
| 93 | 
         
            +
              "decoder_mlp_layers": [],
         
     | 
| 94 | 
         
            +
              "nonlinearity": "elu",
         
     | 
| 95 | 
         
            +
              "policy_initialization": "orthogonal",
         
     | 
| 96 | 
         
            +
              "policy_init_gain": 1.0,
         
     | 
| 97 | 
         
            +
              "actor_critic_share_weights": true,
         
     | 
| 98 | 
         
            +
              "adaptive_stddev": true,
         
     | 
| 99 | 
         
            +
              "continuous_tanh_scale": 0.0,
         
     | 
| 100 | 
         
            +
              "initial_stddev": 1.0,
         
     | 
| 101 | 
         
            +
              "use_env_info_cache": false,
         
     | 
| 102 | 
         
            +
              "env_gpu_actions": false,
         
     | 
| 103 | 
         
            +
              "env_gpu_observations": true,
         
     | 
| 104 | 
         
            +
              "env_frameskip": 1,
         
     | 
| 105 | 
         
            +
              "env_framestack": 1,
         
     | 
| 106 | 
         
            +
              "pixel_format": "CHW",
         
     | 
| 107 | 
         
            +
              "use_record_episode_statistics": false,
         
     | 
| 108 | 
         
            +
              "episode_counter": false,
         
     | 
| 109 | 
         
            +
              "with_wandb": true,
         
     | 
| 110 | 
         
            +
              "wandb_user": "platypus",
         
     | 
| 111 | 
         
            +
              "wandb_project": "metta",
         
     | 
| 112 | 
         
            +
              "wandb_group": null,
         
     | 
| 113 | 
         
            +
              "wandb_job_type": "SF",
         
     | 
| 114 | 
         
            +
              "wandb_tags": [],
         
     | 
| 115 | 
         
            +
              "with_pbt": false,
         
     | 
| 116 | 
         
            +
              "pbt_mix_policies_in_one_env": true,
         
     | 
| 117 | 
         
            +
              "pbt_period_env_steps": 5000000,
         
     | 
| 118 | 
         
            +
              "pbt_start_mutation": 20000000,
         
     | 
| 119 | 
         
            +
              "pbt_replace_fraction": 0.3,
         
     | 
| 120 | 
         
            +
              "pbt_mutation_rate": 0.15,
         
     | 
| 121 | 
         
            +
              "pbt_replace_reward_gap": 0.1,
         
     | 
| 122 | 
         
            +
              "pbt_replace_reward_gap_absolute": 1e-06,
         
     | 
| 123 | 
         
            +
              "pbt_optimize_gamma": false,
         
     | 
| 124 | 
         
            +
              "pbt_target_objective": "true_objective",
         
     | 
| 125 | 
         
            +
              "pbt_perturb_min": 1.1,
         
     | 
| 126 | 
         
            +
              "pbt_perturb_max": 1.5,
         
     | 
| 127 | 
         
            +
              "env_cfg": "{\"name\": \"GDY-MettaGrid\", \"_target_\": \"env.griddly.mettagrid.gym_env.MettaGridGymEnv\", \"max_action_value\": 10, \"game_builder\": {\"_target_\": \"env.griddly.mettagrid.game_builder.MettaGridGameBuilder\", \"obs_width\": 11, \"obs_height\": 11, \"max_steps\": 1000, \"tile_size\": 16, \"num_agents\": 20, \"objects\": {\"agent\": {\"initial_energy\": 100, \"max_energy\": 500, \"max_inventory\": 5, \"freeze_duration\": 10, \"hp\": 1, \"upkeep\": {\"shield\": 1}}, \"altar\": {\"hp\": 30, \"cooldown\": 2, \"cost\": 100}, \"converter\": {\"hp\": 30, \"cooldown\": 2, \"energy_output\": 50, \"cost\": 0}, \"generator\": {\"hp\": 30, \"cooldown\": 5, \"initial_resources\": 30, \"cost\": 0}, \"wall\": {\"density\": 0.01, \"hp\": 10}}, \"actions\": {\"move\": {\"cost\": 0}, \"rotate\": {\"cost\": 0}, \"jump\": {\"cost\": 3}, \"shield\": {\"cost\": 0}, \"drop\": {\"cost\": 1}, \"use\": {\"cost\": 0}, \"attack\": {\"cost\": 5, \"damage\": 5}}, \"map\": {\"layout\": [[\"base\", \"wild_1\", \"base\"], [\"wild_2\", \"center\", \"wild_2\"], [\"base\", \"wild_1\", \"base\"]], \"room\": {\"width\": 25, \"height\": 25, \"num_agents\": 5, \"objects\": {\"agent\": 5, \"altar\": 1, \"converter\": 3, \"generator\": 15, \"wall\": 10}}, \"wild_1\": {\"width\": 10, \"height\": 15, \"border\": 0, \"objects\": {\"agent\": 0, \"altar\": 1, \"converter\": 1, \"generator\": 5, \"wall\": 5}}, \"wild_2\": {\"width\": 15, \"height\": 10, \"border\": 0, \"objects\": {\"agent\": 0, \"altar\": 1, \"converter\": 1, \"generator\": 5, \"wall\": 5}}, \"center\": {\"width\": 10, \"height\": 10, \"border\": 0, \"objects\": {\"agent\": 0, \"altar\": 2, \"converter\": 5, \"generator\": 10, \"wall\": 20}}, \"base\": {\"width\": 15, \"height\": 15, \"border\": 1, \"objects\": {\"agent\": 5, \"altar\": 1, \"converter\": 3, \"generator\": 5, \"wall\": 5}}}}}",
         
     | 
| 128 | 
         
            +
              "agent_cfg": "{\"_target_\": \"agent.metta_agent.MettaAgent\", \"observation_encoders\": {\"grid_obs\": {\"feature_names\": [], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 512, \"layers\": 4}, \"global_vars\": {\"feature_names\": [], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}, \"last_action\": {\"feature_names\": [\"last_action_id\", \"last_action_val\"], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}, \"last_reward\": {\"feature_names\": [\"last_reward\"], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}}, \"fc\": {\"layers\": 3, \"output_dim\": 512}, \"decoder\": {\"_target_\": \"agent.decoder.Decoder\"}, \"core\": {\"_target_\": \"sample_factory.model.core.ModelCoreRNN\", \"rnn_type\": \"gru\", \"rnn_num_layers\": 1, \"rnn_size\": 512}}",
         
     | 
| 129 | 
         
            +
              "command_line": "--aux_loss_coef=0 --recurrence=256 --rollout=256 --value_loss_coeff=0.976 --exploration_loss=symmetric_kl --exploration_loss_coeff=0.002 --policy_initialization=orthogonal --learning_rate=0.0001 --max_policy_lag=50 --nonlinearity=elu --load_checkpoint_kind=latest --normalize_input=False --seed=0 --batch_size=16384 --decorrelate_experience_max_seconds=150 --train_for_env_steps=9999999999999 --with_wandb=True --wandb_user=platypus --wandb_project=metta --experiment=p2.metta.4 --rnn_type=gru --rnn_num_layers=1 --rnn_size=512 --env=GDY-MettaGrid --env_cfg={\"name\": \"GDY-MettaGrid\", \"_target_\": \"env.griddly.mettagrid.gym_env.MettaGridGymEnv\", \"game_builder\": {\"_target_\": \"env.griddly.mettagrid.game_builder.MettaGridGameBuilder\", \"obs_width\": 11, \"obs_height\": 11, \"max_steps\": 1000, \"tile_size\": 16, \"width\": 40, \"height\": 40, \"objects\": {\"agent\": {\"count\": 20, \"initial_energy\": 100, \"max_energy\": 500, \"max_inventory\": 5, \"freeze_duration\": 10, \"hp\": 1, \"upkeep\": {\"shield\": 1}}, \"altar\": {\"hp\": 30, \"count\": 5, \"cooldown\": 2, \"cost\": 100}, \"converter\": {\"hp\": 30, \"count\": 10, \"cooldown\": 2, \"energy_output\": 50, \"cost\": 0}, \"generator\": {\"hp\": 30, \"count\": 50, \"cooldown\": 50, \"initial_resources\": 100, \"cost\": 0}, \"wall\": {\"density\": 0.01, \"hp\": 10}, \"charger\": {\"count\": 10}}, \"actions\": {\"move\": {\"cost\": 0}, \"rotate\": {\"cost\": 0}, \"jump\": {\"cost\": 3}, \"shield\": {\"cost\": 0}, \"drop\": {\"cost\": 1}, \"use\": {\"cost\": 0}, \"attack\": {\"cost\": 5, \"damage\": 5}}}, \"global_features\": [\"conf:agent:energy:initial\", \"conf:agent:energy:max\", \"conf:altar:cooldown\", \"conf:altar:cost\", \"conf:attack:damage\", \"conf:attack:freeze_duration\", \"conf:charger:cooldown\", \"conf:charger:energy\", \"conf:cost:attack\", \"conf:cost:frozen\", \"conf:cost:jump\", \"conf:cost:move\", \"conf:cost:rotate\", \"conf:cost:shield:upkeep\", \"conf:cost:shield\", \"conf:generator:cooldown\", \"conf:gift:energy\"], \"grid_features\": [\"agent\", \"altar\", \"charger\", \"generator\", \"wall\", \"agent:dir\", \"agent:energy\", \"agent:frozen\", \"agent:id\", \"agent:inv:1\", \"agent:inv:2\", \"agent:inv:3\", \"agent:shield\", \"agent:species\", \"altar:ready\", \"charger:bonus\", \"charger:input:1\", \"charger:input:2\", \"charger:input:3\", \"charger:output\", \"charger:ready\", \"generator:ready\", \"generator:resource\"], \"actions\": [\"rotate\", \"move\", \"jump\", \"use\", \"gift\", \"shield\", \"attack\"], \"max_action_value\": 10} --agent_cfg={\"_target_\": \"agent.metta_agent.MettaAgent\", \"observation_encoders\": {\"grid_obs\": {\"feature_names\": [], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 512, \"layers\": 4}, \"global_vars\": {\"feature_names\": [], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}, \"last_action\": {\"feature_names\": [\"last_action_id\", \"last_action_val\"], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}, \"last_reward\": {\"feature_names\": [\"last_reward\"], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}}, \"fc\": {\"layers\": 3, \"output_dim\": 512}, \"decoder\": {\"_target_\": \"agent.decoder.Decoder\"}, \"core\": {\"_target_\": \"sample_factory.model.core.ModelCoreRNN\", \"rnn_type\": \"gru\", \"rnn_num_layers\": 1, \"rnn_size\": 512}}",
         
     | 
| 130 | 
         
            +
              "cli_args": {
         
     | 
| 131 | 
         
            +
                "env": "GDY-MettaGrid",
         
     | 
| 132 | 
         
            +
                "experiment": "p2.metta.4",
         
     | 
| 133 | 
         
            +
                "seed": 0,
         
     | 
| 134 | 
         
            +
                "max_policy_lag": 50,
         
     | 
| 135 | 
         
            +
                "batch_size": 16384,
         
     | 
| 136 | 
         
            +
                "rollout": 256,
         
     | 
| 137 | 
         
            +
                "recurrence": 256,
         
     | 
| 138 | 
         
            +
                "exploration_loss_coeff": 0.002,
         
     | 
| 139 | 
         
            +
                "value_loss_coeff": 0.976,
         
     | 
| 140 | 
         
            +
                "aux_loss_coeff": 0.0,
         
     | 
| 141 | 
         
            +
                "exploration_loss": "symmetric_kl",
         
     | 
| 142 | 
         
            +
                "learning_rate": 0.0001,
         
     | 
| 143 | 
         
            +
                "normalize_input": false,
         
     | 
| 144 | 
         
            +
                "decorrelate_experience_max_seconds": 150,
         
     | 
| 145 | 
         
            +
                "train_for_env_steps": 9999999999999,
         
     | 
| 146 | 
         
            +
                "load_checkpoint_kind": "latest",
         
     | 
| 147 | 
         
            +
                "rnn_size": 512,
         
     | 
| 148 | 
         
            +
                "rnn_type": "gru",
         
     | 
| 149 | 
         
            +
                "rnn_num_layers": 1,
         
     | 
| 150 | 
         
            +
                "nonlinearity": "elu",
         
     | 
| 151 | 
         
            +
                "policy_initialization": "orthogonal",
         
     | 
| 152 | 
         
            +
                "with_wandb": true,
         
     | 
| 153 | 
         
            +
                "wandb_user": "platypus",
         
     | 
| 154 | 
         
            +
                "wandb_project": "metta",
         
     | 
| 155 | 
         
            +
                "env_cfg": "{\"name\": \"GDY-MettaGrid\", \"_target_\": \"env.griddly.mettagrid.gym_env.MettaGridGymEnv\", \"game_builder\": {\"_target_\": \"env.griddly.mettagrid.game_builder.MettaGridGameBuilder\", \"obs_width\": 11, \"obs_height\": 11, \"max_steps\": 1000, \"tile_size\": 16, \"width\": 40, \"height\": 40, \"objects\": {\"agent\": {\"count\": 20, \"initial_energy\": 100, \"max_energy\": 500, \"max_inventory\": 5, \"freeze_duration\": 10, \"hp\": 1, \"upkeep\": {\"shield\": 1}}, \"altar\": {\"hp\": 30, \"count\": 5, \"cooldown\": 2, \"cost\": 100}, \"converter\": {\"hp\": 30, \"count\": 10, \"cooldown\": 2, \"energy_output\": 50, \"cost\": 0}, \"generator\": {\"hp\": 30, \"count\": 50, \"cooldown\": 50, \"initial_resources\": 100, \"cost\": 0}, \"wall\": {\"density\": 0.01, \"hp\": 10}, \"charger\": {\"count\": 10}}, \"actions\": {\"move\": {\"cost\": 0}, \"rotate\": {\"cost\": 0}, \"jump\": {\"cost\": 3}, \"shield\": {\"cost\": 0}, \"drop\": {\"cost\": 1}, \"use\": {\"cost\": 0}, \"attack\": {\"cost\": 5, \"damage\": 5}}}, \"global_features\": [\"conf:agent:energy:initial\", \"conf:agent:energy:max\", \"conf:altar:cooldown\", \"conf:altar:cost\", \"conf:attack:damage\", \"conf:attack:freeze_duration\", \"conf:charger:cooldown\", \"conf:charger:energy\", \"conf:cost:attack\", \"conf:cost:frozen\", \"conf:cost:jump\", \"conf:cost:move\", \"conf:cost:rotate\", \"conf:cost:shield:upkeep\", \"conf:cost:shield\", \"conf:generator:cooldown\", \"conf:gift:energy\"], \"grid_features\": [\"agent\", \"altar\", \"charger\", \"generator\", \"wall\", \"agent:dir\", \"agent:energy\", \"agent:frozen\", \"agent:id\", \"agent:inv:1\", \"agent:inv:2\", \"agent:inv:3\", \"agent:shield\", \"agent:species\", \"altar:ready\", \"charger:bonus\", \"charger:input:1\", \"charger:input:2\", \"charger:input:3\", \"charger:output\", \"charger:ready\", \"generator:ready\", \"generator:resource\"], \"actions\": [\"rotate\", \"move\", \"jump\", \"use\", \"gift\", \"shield\", \"attack\"], \"max_action_value\": 10}",
         
     | 
| 156 | 
         
            +
                "agent_cfg": "{\"_target_\": \"agent.metta_agent.MettaAgent\", \"observation_encoders\": {\"grid_obs\": {\"feature_names\": [], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 512, \"layers\": 4}, \"global_vars\": {\"feature_names\": [], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}, \"last_action\": {\"feature_names\": [\"last_action_id\", \"last_action_val\"], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}, \"last_reward\": {\"feature_names\": [\"last_reward\"], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}}, \"fc\": {\"layers\": 3, \"output_dim\": 512}, \"decoder\": {\"_target_\": \"agent.decoder.Decoder\"}, \"core\": {\"_target_\": \"sample_factory.model.core.ModelCoreRNN\", \"rnn_type\": \"gru\", \"rnn_num_layers\": 1, \"rnn_size\": 512}}"
         
     | 
| 157 | 
         
            +
              },
         
     | 
| 158 | 
         
            +
              "git_hash": "7864b034e8faa45a8cef257cdd0b4d3b2b2549f3",
         
     | 
| 159 | 
         
            +
              "git_repo_name": "https://github.com/daveey/metta.git",
         
     | 
| 160 | 
         
            +
              "wandb_unique_id": "p2.metta.4_20240605_175031_058004"
         
     | 
| 161 | 
         
            +
            }
         
     | 
    	
        git.diff
    ADDED
    
    | 
         
            File without changes
         
     | 
    	
        replay.mp4
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:7fd1f4b5380956f834d3df0c89e055f5a3584825d0a85f6cfb2c673ff4c18db8
         
     | 
| 3 | 
         
            +
            size 1949240
         
     | 
    	
        sf_log.txt
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:4e251b8a808735267249b108e57de0871afa1a4236625da2881391376d8fa29e
         
     | 
| 3 | 
         
            +
            size 31982556
         
     |