Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -220.49 +/- 77.55
+      value: -1196.56 +/- 144.96
       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 0x7fe97263d5a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe97263d630>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe97263d6c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe97263d750>", "_build": "<function ActorCriticPolicy._build at 0x7fe97263d7e0>", "forward": "<function ActorCriticPolicy.forward at 0x7fe97263d870>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fe97263d900>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe97263d990>", "_predict": "<function ActorCriticPolicy._predict at 0x7fe97263da20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe97263dab0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe97263db40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe97263dbd0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fe9725d63c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1024, "_total_timesteps": 10, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1715159358317254673, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAE2GxL12LMI/a4UgvwQ1Nz6Xc/o9czpdPgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -101.4, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVcgEAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwFVf5v99+gGMAWyUS0CMAXSURz//+ZkTYdyUdX2UKGgGR8B3TZF5OafBaAdLYWgIR0ABDOTq0MPSdX2UKGgGR8BjKxKQJXyRaAdLWWgIR0ACI4EOiFj/dX2UKGgGR8B04rK2a2F4aAdLfWgIR0ADnGlyimEXdX2UKGgGR8BhZ0+V1Oj7aAdLcmgIR0AE3bTMJQchdX2UKGgGR8AZaW0JF9a2aAdLi2gIR0AGaDRMN+b3dX2UKGgGR8Bgr+U4aP0aaAdLRmgIR0AHNHjIaLn+dX2UKGgGR8Bj1d98Z1mraAdLRmgIR0AIT2Jzkp7UdX2UKGgGR8BqIOlj3EhraAdLWmgIR0AJuxbB42S/dX2UKGgGR8BZxNutOmBOaAdLRGgIR0AKubqhUR4AdX2UKGgGR8B3LuT9sJpnaAdLU2gIR0AL5UDMeOn3dWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 4, "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:": "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", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "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": "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 0x795dac5daa70>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x795dac5dab00>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x795dac5dab90>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x795dac5dac20>", "_build": "<function ActorCriticPolicy._build at 0x795dac5dacb0>", "forward": "<function ActorCriticPolicy.forward at 0x795dac5dad40>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x795dac5dadd0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x795dac5dae60>", "_predict": "<function ActorCriticPolicy._predict at 0x795dac5daef0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x795dac5daf80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x795dac5db010>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x795dac5db0a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x795dac5d6fc0>"}, "verbose": 0, "policy_kwargs": {}, "num_timesteps": 25600, "_total_timesteps": 25000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1715267606692551837, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAK3tVj5lbIk/GB1pu4tchr7Kek8/NpyRPgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.02400000000000002, "_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": 100, "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:": "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", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "n_steps": 1024, "gamma": 0.59, "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"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cc9eece6a90eb72d4881b84ae51995809df0689e1ee1366ba32edd00af0fda8
-size 143988
+oid sha256:7ea7c6db3ea1947d01340ea7d69a44ce711a00866e7a7263b991bdd40e9a6793
+size 147583

ppo-LunarLander-v2/data

@@ -4,34 +4,34 @@
         ":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 0x7fe97263d5a0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe97263d630>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe97263d6c0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe97263d750>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fe97263d7e0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fe97263d870>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fe97263d900>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe97263d990>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fe97263da20>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe97263dab0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe97263db40>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe97263dbd0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x795dac5daa70>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x795dac5dab00>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x795dac5dab90>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x795dac5dac20>",
+        "_build": "<function ActorCriticPolicy._build at 0x795dac5dacb0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x795dac5dad40>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x795dac5dadd0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x795dac5dae60>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x795dac5daef0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x795dac5daf80>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x795dac5db010>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x795dac5db0a0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fe9725d63c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x795dac5d6fc0>"
     },
-    "verbose": 1,
+    "verbose": 0,
     "policy_kwargs": {},
-    "num_timesteps": 1024,
-    "_total_timesteps": 10,
+    "num_timesteps": 25600,
+    "_total_timesteps": 25000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1715159358317254673,
+    "start_time": 1715267606692551837,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAE2GxL12LMI/a4UgvwQ1Nz6Xc/o9czpdPgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAK3tVj5lbIk/GB1pu4tchr7Kek8/NpyRPgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,17 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -101.4,
+    "_current_progress_remaining": -0.02400000000000002,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 4,
+    "_n_updates": 100,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -69,7 +69,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "n": "4",
         "start": "0",
         "_shape": [],
@@ -78,7 +78,7 @@
     },
     "n_envs": 1,
     "n_steps": 1024,
-    "gamma": 0.999,
+    "gamma": 0.59,
     "gae_lambda": 0.98,
     "ent_coef": 0.01,
     "vf_coef": 0.5,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1b48b7de2988b081b6a685014e38da87ee227f9a664b48dc7430401fcfdad08
+oid sha256:81e23eb562d34e6935751041f5171468ea6ce5708bef895f34fd4c8b59715169
 size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a849147802482a36be009da6ae3622ae2b775b10a3cdde76024f95a350cf862d
+oid sha256:5a6422aba738d17ca8a37837294637609b79889f99f5c3acebc362960dcd4a34
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": -220.4913886, "std_reward": 77.54835154792313, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-08T09:10:45.824622"}
+{"mean_reward": -1196.5648176999998, "std_reward": 144.95721908277335, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-09T15:14:57.039296"}