second commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 252.51 +/- 15.59
+      value: 203.37 +/- 88.94
       name: mean_reward
       verified: false
 ---

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 0x17c09f7e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x17c09f880>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x17c09f920>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x17c09f9c0>", "_build": "<function ActorCriticPolicy._build at 0x17c09fa60>", "forward": "<function ActorCriticPolicy.forward at 0x17c09fb00>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x17c09fba0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x17c09fc40>", "_predict": "<function ActorCriticPolicy._predict at 0x17c09fce0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x17c09fd80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x17c09fe20>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x17c09fec0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x17c0a1cc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1695066768853270000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABr0hr1orLq8lO6GO/6oNz1mdr27etnPugAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "_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": 3908, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "macOS-13.5.2-arm64-arm-64bit Darwin Kernel Version 22.6.0: Wed Jul  5 22:22:05 PDT 2023; root:xnu-8796.141.3~6/RELEASE_ARM64_T6000", "Python": "3.11.5", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.0.dev20230918", "GPU Enabled": "False", "Numpy": "1.26.0", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1"}}
+{"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 0x28e6cb240>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x28e6cb2e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x28e6cb380>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x28e6cb420>", "_build": "<function ActorCriticPolicy._build at 0x28e6cb4c0>", "forward": "<function ActorCriticPolicy.forward at 0x28e6cb560>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x28e6cb600>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x28e6cb6a0>", "_predict": "<function ActorCriticPolicy._predict at 0x28e6cb740>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x28e6cb7e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x28e6cb880>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x28e6cb920>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x28e6d4d00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1695066768853270000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABr0hr1orLq8lO6GO/6oNz1mdr27etnPugAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "_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": 3908, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "macOS-13.5.2-arm64-arm-64bit Darwin Kernel Version 22.6.0: Wed Jul  5 22:22:05 PDT 2023; root:xnu-8796.141.3~6/RELEASE_ARM64_T6000", "Python": "3.11.5", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.0.dev20230918", "GPU Enabled": "False", "Numpy": "1.26.0", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a8b0076869dbf11467225736dd48ed58d81f6b75b44c4a23b7b727faacca6b0
-size 147194
+oid sha256:35fe2d50048ce3a1fe217e9b9dd33877931106a065d1031de41a58cbaad067b6
+size 147174

ppo-LunarLander-v2/data

@@ -4,20 +4,20 @@
         ":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 0x17c09f7e0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x17c09f880>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x17c09f920>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x17c09f9c0>",
-        "_build": "<function ActorCriticPolicy._build at 0x17c09fa60>",
-        "forward": "<function ActorCriticPolicy.forward at 0x17c09fb00>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x17c09fba0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x17c09fc40>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x17c09fce0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x17c09fd80>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x17c09fe20>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x17c09fec0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x28e6cb240>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x28e6cb2e0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x28e6cb380>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x28e6cb420>",
+        "_build": "<function ActorCriticPolicy._build at 0x28e6cb4c0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x28e6cb560>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x28e6cb600>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x28e6cb6a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x28e6cb740>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x28e6cb7e0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x28e6cb880>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x28e6cb920>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x17c0a1cc0>"
+        "_abc_impl": "<_abc._abc_data object at 0x28e6d4d00>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -52,6 +52,21 @@
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
     "_n_updates": 3908,
+    "n_steps": 1024,
+    "gamma": 0.999,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 4,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -69,7 +84,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
         "n": "4",
         "start": "0",
         "_shape": [],
@@ -77,21 +92,6 @@
         "_np_random": null
     },
     "n_envs": 1,
-    "n_steps": 1024,
-    "gamma": 0.999,
-    "gae_lambda": 0.98,
-    "ent_coef": 0.01,
-    "vf_coef": 0.5,
-    "max_grad_norm": 0.5,
-    "batch_size": 64,
-    "n_epochs": 4,
-    "clip_range": {
-        ":type:": "<class 'function'>",
-        ":serialized:": "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"
-    },
-    "clip_range_vf": null,
-    "normalize_advantage": true,
-    "target_kl": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935999734ef242de88d6d6e5da876acd64fda5f2a46149a2cf25a6ee7eddead8
-size 88042
+oid sha256:c49675ead3903042b96f042c2e9b6c8a46b3f8214c6de044a9fa6a9b4662e1da
+size 87978

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d199624d71169913694fd1a8d1c00a2f582e83242ef22dea54836c5dca006b2
+oid sha256:9e6fbe514886344ab47b974424e1a8ff87a589f6e2ac2f6b6a36a9098c0cec18
 size 43634

results.json

@@ -1 +1 @@
-{"mean_reward": 252.51282809999998, "std_reward": 15.592081850792285, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-18T17:29:17.608995"}
+{"mean_reward": 203.3685428, "std_reward": 88.9429588652746, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-18T17:36:22.273251"}