Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 228.09 +/- 22.91
+      value: 244.28 +/- 17.38
       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 0x7efcf69c7d80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efcf69c7e20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efcf69c7ec0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efcf69c7f60>", "_build": "<function ActorCriticPolicy._build at 0x7efcf69d4040>", "forward": "<function ActorCriticPolicy.forward at 0x7efcf69d40e0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7efcf69d4180>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efcf69d4220>", "_predict": "<function ActorCriticPolicy._predict at 0x7efcf69d42c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efcf69d4360>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efcf69d4400>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efcf69d44a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7efcf69cddc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1720358066659356826, "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:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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-5.15.153.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Mar 29 23:14:13 UTC 2024", "Python": "3.11.9", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.1", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "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 0x7fe92f2dfd80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe92f2dfe20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe92f2dfec0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe92f2dff60>", "_build": "<function ActorCriticPolicy._build at 0x7fe92f2f4040>", "forward": "<function ActorCriticPolicy.forward at 0x7fe92f2f40e0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fe92f2f4180>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe92f2f4220>", "_predict": "<function ActorCriticPolicy._predict at 0x7fe92f2f42c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe92f2f4360>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe92f2f4400>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe92f2f44a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fe92f2e5dc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1720358066659356826, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "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-5.15.153.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Mar 29 23:14:13 UTC 2024", "Python": "3.11.9", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.1", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd92d209947a6bbae3015867cf77147ad2cb3ea4013e97e0b9d5dd3b72903e6c
-size 148195
+oid sha256:688b5e4a7e488bf8af3d9462582872c3237bf9e59e735e2f086884e3ec508109
+size 147436

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 0x7efcf69c7d80>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efcf69c7e20>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efcf69c7ec0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efcf69c7f60>",
-        "_build": "<function ActorCriticPolicy._build at 0x7efcf69d4040>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7efcf69d40e0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7efcf69d4180>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efcf69d4220>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7efcf69d42c0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efcf69d4360>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efcf69d4400>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efcf69d44a0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fe92f2dfd80>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe92f2dfe20>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe92f2dfec0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe92f2dff60>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fe92f2f4040>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fe92f2f40e0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fe92f2f4180>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe92f2f4220>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fe92f2f42c0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe92f2f4360>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe92f2f4400>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe92f2f44a0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7efcf69cddc0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fe92f2e5dc0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -29,10 +29,7 @@
     "start_time": 1720358066659356826,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
-    "_last_obs": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
-    },
+    "_last_obs": null,
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
         ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
@@ -69,7 +66,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
         "n": "4",
         "start": "0",
         "_shape": [],

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42da331375fa8e893c7447ebb7eb34c2b61ca03db26c34d200d0226d7bb0139
-size 88362
+oid sha256:5b0bc8d1a82e715e1811169d0eb05cc8aab4591fdd9670b20fde2bc8a9d72d5e
+size 88490

results.json

@@ -1 +1 @@
-{"mean_reward": 228.0919722056811, "std_reward": 22.90806156631454, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-07T22:41:00.410596"}
+{"mean_reward": 244.2834762459789, "std_reward": 17.379082600543633, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-07T22:47:42.639466"}