Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 256.68 +/- 36.45
+      value: 273.98 +/- 16.32
       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 0x7daf6b2ce050>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7daf6b2ce0e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7daf6b2ce170>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7daf6b2ce200>", "_build": "<function ActorCriticPolicy._build at 0x7daf6b2ce290>", "forward": "<function ActorCriticPolicy.forward at 0x7daf6b2ce320>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7daf6b2ce3b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7daf6b2ce440>", "_predict": "<function ActorCriticPolicy._predict at 0x7daf6b2ce4d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7daf6b2ce560>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7daf6b2ce5f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7daf6b2ce680>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7daf6b2d8cc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1001472, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1711416470252775850, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAHbYVL4n3w29msaFuyq9F7o6k3k+8mDaOgAAgD8AAIA/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": -0.0014719999999999178, "_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": 1956, "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": 2048, "gamma": 0.99, "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": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
+{"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 0x7daf6b2ce050>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7daf6b2ce0e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7daf6b2ce170>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7daf6b2ce200>", "_build": "<function ActorCriticPolicy._build at 0x7daf6b2ce290>", "forward": "<function ActorCriticPolicy.forward at 0x7daf6b2ce320>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7daf6b2ce3b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7daf6b2ce440>", "_predict": "<function ActorCriticPolicy._predict at 0x7daf6b2ce4d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7daf6b2ce560>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7daf6b2ce5f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7daf6b2ce680>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7daf6b2d8cc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1001472, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1711416470252775850, "learning_rate": 0.0, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAHbYVL4n3w29msaFuyq9F7o6k3k+8mDaOgAAgD8AAIA/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": -0.0014719999999999178, "_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": 1956, "n_steps": 2048, "gamma": 0.99, "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURwAAAAAAAAAAhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64e510de3aa2e70064a9d1ae1ca39da0756586c0df403534f263b7d7110699f9
-size 147312
+oid sha256:8346f78371a4ed05078e574db03878fde65e1f2ee737c1f64c645db8a1ec988c
+size 147141

ppo-LunarLander-v2/data

@@ -27,7 +27,7 @@
     "seed": null,
     "action_noise": null,
     "start_time": 1711416470252775850,
-    "learning_rate": 0.0003,
+    "learning_rate": 0.0,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -52,6 +52,21 @@
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
     "_n_updates": 1956,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "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": [],
@@ -77,23 +92,8 @@
         "_np_random": null
     },
     "n_envs": 1,
-    "n_steps": 2048,
-    "gamma": 0.99,
-    "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
-    },
-    "clip_range_vf": null,
-    "normalize_advantage": true,
-    "target_kl": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":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:f14d51b842c1f7fdae42dbfd20b83cbca2b2e94a7edd98fe7973dae3a92306cb
-size 88362
+oid sha256:3b14edb591339099bbd8feed0504e2c1b0889bed0d56e40c47012be2c8e67268
+size 88490

results.json

@@ -1 +1 @@
-{"mean_reward": 256.6812693863807, "std_reward": 36.45246849637813, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-26T02:04:40.261846"}
+{"mean_reward": 273.9826836853065, "std_reward": 16.318064912010136, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-26T02:06:53.491130"}