Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -676.97 +/- 221.11
+      value: 241.58 +/- 33.25
       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 0x78cfc865edd0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78cfc865ee60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78cfc865eef0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78cfc865ef80>", "_build": "<function ActorCriticPolicy._build at 0x78cfc865f010>", "forward": "<function ActorCriticPolicy.forward at 0x78cfc865f0a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x78cfc865f130>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78cfc865f1c0>", "_predict": "<function ActorCriticPolicy._predict at 0x78cfc865f250>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78cfc865f2e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78cfc865f370>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x78cfc865f400>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78cfc8601180>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "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": 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": "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": "2.4.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "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 0x7ecd60e6ad40>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ecd60e6add0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ecd60e6ae60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ecd60e6aef0>", "_build": "<function ActorCriticPolicy._build at 0x7ecd60e6af80>", "forward": "<function ActorCriticPolicy.forward at 0x7ecd60e6b010>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ecd60e6b0a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ecd60e6b130>", "_predict": "<function ActorCriticPolicy._predict at 0x7ecd60e6b1c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ecd60e6b250>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ecd60e6b2e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ecd60e6b370>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ecd6a237300>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1725518511778194005, "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": 248, "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": 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:": "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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"}, "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": "2.4.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "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:d5a662f25afc91960193c28877e73d66cf7ce57954102730ddf975fa39ce8cfe
-size 55178
+oid sha256:25cfde52bb807137c89bd9b46e24dfe4444c61b4c8c93571a7b89f502b84d124
+size 148076

ppo-LunarLander-v2/data

@@ -4,42 +4,54 @@
         ":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 0x78cfc865edd0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78cfc865ee60>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78cfc865eef0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78cfc865ef80>",
-        "_build": "<function ActorCriticPolicy._build at 0x78cfc865f010>",
-        "forward": "<function ActorCriticPolicy.forward at 0x78cfc865f0a0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x78cfc865f130>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78cfc865f1c0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x78cfc865f250>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78cfc865f2e0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78cfc865f370>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x78cfc865f400>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7ecd60e6ad40>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ecd60e6add0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ecd60e6ae60>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ecd60e6aef0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ecd60e6af80>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ecd60e6b010>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ecd60e6b0a0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ecd60e6b130>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ecd60e6b1c0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ecd60e6b250>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ecd60e6b2e0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ecd60e6b370>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x78cfc8601180>"
+        "_abc_impl": "<_abc._abc_data object at 0x7ecd6a237300>"
     },
     "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": 0.0,
+    "start_time": 1725518511778194005,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
-    "_last_obs": null,
-    "_last_episode_starts": 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": 1.0,
+    "_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": 248,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13dbf41e305d3a0b52e13b973ece0bb28ffca5bcf57636bcf9b68102feec544e
-size 1120
+oid sha256:60759d57bc457dc505eef39b90afc9e1c5dfe73558f52d3deabe7ac8f53194a5
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7eb4ebdbefa18a5a6f80aefb77b8c3735e575d00687b1ede66fdaa06d830fcc
+oid sha256:8ba0af2b618ef185a2aa08b321a3964387fb9f69794114b94457103c31ef057d
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": -676.9672661000001, "std_reward": 221.11150580310292, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-28T14:34:08.652882"}
+{"mean_reward": 241.57602341906, "std_reward": 33.252517102428925, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-05T07:33:18.696659"}