PPO_lr_steps&epoches+

README.md

@@ -6,7 +6,7 @@ tags:
 - reinforcement-learning
 - stable-baselines3
 model-index:
-- name: PPO_lr_steps&epoches+
+- name: PPO
   results:
   - task:
       type: reinforcement-learning
@@ -16,13 +16,13 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -309.63 +/- 176.47
+      value: 280.03 +/- 20.25
       name: mean_reward
       verified: false
 ---
 
-# **PPO_lr_steps&epoches+** Agent playing **LunarLander-v2**
-This is a trained model of a **PPO_lr_steps&epoches+** agent playing **LunarLander-v2**
+# **PPO** Agent playing **LunarLander-v2**
+This is a trained model of a **PPO** agent playing **LunarLander-v2**
 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
 
 ## Usage (with Stable-baselines3)

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f8e22093040>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8e220930d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8e22093160>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8e220931f0>", "_build": "<function ActorCriticPolicy._build at 0x7f8e22093280>", "forward": "<function ActorCriticPolicy.forward at 0x7f8e22093310>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f8e220933a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8e22093430>", "_predict": "<function ActorCriticPolicy._predict at 0x7f8e220934c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8e22093550>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8e220935e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8e22093670>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f8e220943c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 42, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f95ce3a8430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f95ce3a84c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f95ce3a8550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f95ce3a85e0>", "_build": "<function ActorCriticPolicy._build at 0x7f95ce3a8670>", "forward": "<function ActorCriticPolicy.forward at 0x7f95ce3a8700>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f95ce3a8790>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f95ce3a8820>", "_predict": "<function ActorCriticPolicy._predict at 0x7f95ce3a88b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f95ce3a8940>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f95ce3a89d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f95ce3a8a60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f95ce3a4b00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1681054285944799058, "learning_rate": 0.0, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1302, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 42, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVwwEAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUtDQwRkAVMAlE5HAAAAAAAAAACGlCmMAV+UhZSMHjxpcHl0aG9uLWlucHV0LTMtMDgwZmE5ZGMwNDdjPpSMCDxsYW1iZGE+lEsNQwCUKSl0lFKUfZQojAtfX3BhY2thZ2VfX5ROjAhfX25hbWVfX5SMCF9fbWFpbl9flHVOTk50lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaBZ9lH2UKGgTaA2MDF9fcXVhbG5hbWVfX5RoDYwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoFIwHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5ROjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a4e528a7f7735807a0be594a20bb53176ca0947d35c4c222ff8b2d646052927
-size 53040
+oid sha256:400f408c827f6dc68594d705b4cd4628720e7f4c1a8a9a394de57033765adbf5
+size 147065

ppo-LunarLander-v2/data

@@ -4,49 +4,76 @@
         ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
-        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f8e22093040>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8e220930d0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8e22093160>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8e220931f0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f8e22093280>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f8e22093310>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f8e220933a0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8e22093430>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f8e220934c0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8e22093550>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8e220935e0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8e22093670>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f95ce3a8430>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f95ce3a84c0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f95ce3a8550>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f95ce3a85e0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f95ce3a8670>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f95ce3a8700>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f95ce3a8790>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f95ce3a8820>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f95ce3a88b0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f95ce3a8940>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f95ce3a89d0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f95ce3a8a60>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f8e220943c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f95ce3a4b00>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": null,
-    "learning_rate": 0.0003,
+    "start_time": 1681054285944799058,
+    "learning_rate": 0.0,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
     },
-    "_last_obs": null,
-    "_last_episode_starts": null,
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": 1,
+    "_current_progress_remaining": -0.015808000000000044,
     "_stats_window_size": 100,
-    "ep_info_buffer": null,
-    "ep_success_buffer": null,
-    "_n_updates": 0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 1302,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 42,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
     "observation_space": {
         ":type:": "<class 'gym.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "dtype": "float32",
         "_shape": [
             8
@@ -59,26 +86,11 @@
     },
     "action_space": {
         ":type:": "<class 'gym.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        ":serialized:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
         "n": 4,
         "_shape": [],
         "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 16,
-    "n_steps": 2048,
-    "gamma": 0.99,
-    "gae_lambda": 0.95,
-    "ent_coef": 0.01,
-    "vf_coef": 0.5,
-    "max_grad_norm": 0.5,
-    "batch_size": 64,
-    "n_epochs": 42,
-    "clip_range": {
-        ":type:": "<class 'function'>",
-        ":serialized:": "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"
-    },
-    "clip_range_vf": null,
-    "normalize_advantage": true,
-    "target_kl": null
+    "n_envs": 16
 }

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0aa96bf78c4536c6eafd36ce78653aac56f76c12f489666d21b1ace601e8300
-size 687
+oid sha256:b6d7ad50f7b994b8ff0ecc4489d5e8abd11a8cc8563724fdd9c305a172a8e86a
+size 88057

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e26ff027980ae8d98ea46b7f896341b586c018a5bb20cc7544063310de6cfa8b
+oid sha256:0516aca4e56db62a6687b58936d2254620efc887a56e93e3a3915c2205d7d47c
 size 43329

results.json

@@ -1 +1 @@
-{"mean_reward": -309.6290367351379, "std_reward": 176.46768590323123, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-09T15:06:28.497591"}
+{"mean_reward": 280.03199761825465, "std_reward": 20.25110683105718, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-09T16:50:15.784472"}