Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 265.86 +/- 39.47
+      value: 281.29 +/- 15.39
       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 0x7d217fd356c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d217fd35750>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d217fd357e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d217fd35870>", "_build": "<function ActorCriticPolicy._build at 0x7d217fd35900>", "forward": "<function ActorCriticPolicy.forward at 0x7d217fd35990>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d217fd35a20>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d217fd35ab0>", "_predict": "<function ActorCriticPolicy._predict at 0x7d217fd35b40>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d217fd35bd0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d217fd35c60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d217fd35cf0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d217feca740>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1721366968596207012, "learning_rate": 0.0003, "tensorboard_log": null, "_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": 310, "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": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.1+cu121", "GPU Enabled": "False", "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 0x78c7272ac820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78c7272ac8b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78c7272ac940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78c7272ac9d0>", "_build": "<function ActorCriticPolicy._build at 0x78c7272aca60>", "forward": "<function ActorCriticPolicy.forward at 0x78c7272acaf0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x78c7272acb80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78c7272acc10>", "_predict": "<function ActorCriticPolicy._predict at 0x78c7272acca0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78c7272acd30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78c7272acdc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x78c7272ace50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78c727243080>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1721366968596207012, "learning_rate": 0.0003, "tensorboard_log": null, "_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": 310, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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": 16, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.1+cu121", "GPU Enabled": "False", "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:b17bf225a5a3a957640394585b47e00655bc282715230ff1bf7e65d606a75051
-size 147456
+oid sha256:9ebb63adc064d2ff904bf096ea6fd5cfa87f21bb227fd9eb58ab5b175f2ae0b1
+size 147500

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 0x7d217fd356c0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d217fd35750>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d217fd357e0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d217fd35870>",
-        "_build": "<function ActorCriticPolicy._build at 0x7d217fd35900>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7d217fd35990>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d217fd35a20>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d217fd35ab0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7d217fd35b40>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d217fd35bd0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d217fd35c60>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d217fd35cf0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x78c7272ac820>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78c7272ac8b0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78c7272ac940>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78c7272ac9d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x78c7272aca60>",
+        "forward": "<function ActorCriticPolicy.forward at 0x78c7272acaf0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x78c7272acb80>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78c7272acc10>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x78c7272acca0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78c7272acd30>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78c7272acdc0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x78c7272ace50>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7d217feca740>"
+        "_abc_impl": "<_abc._abc_data object at 0x78c727243080>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -52,6 +52,21 @@
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
     "_n_updates": 310,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 10,
+    "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": 16,
-    "n_steps": 2048,
-    "gamma": 0.99,
-    "gae_lambda": 0.95,
-    "ent_coef": 0.0,
-    "vf_coef": 0.5,
-    "max_grad_norm": 0.5,
-    "batch_size": 64,
-    "n_epochs": 10,
-    "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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"

results.json

@@ -1 +1 @@
-{"mean_reward": 265.8612488, "std_reward": 39.472493717091815, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-19T06:10:31.259213"}
+{"mean_reward": 281.28712, "std_reward": 15.39378434147544, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-19T06:22:16.786009"}