Deep RL course

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -406.07 +/- 108.39
+      value: 270.18 +/- 19.10
       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 0x7fd3f59d79d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd3f59d7a60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd3f59d7af0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd3f59d7b80>", "_build": "<function ActorCriticPolicy._build at 0x7fd3f59d7c10>", "forward": "<function ActorCriticPolicy.forward at 0x7fd3f59d7ca0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd3f59d7d30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd3f59d7dc0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd3f59d7e50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd3f59d7ee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd3f59d7f70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd3f59db040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fd3f59d26f0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
+{"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 0x7fd3f59d79d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd3f59d7a60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd3f59d7af0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd3f59d7b80>", "_build": "<function ActorCriticPolicy._build at 0x7fd3f59d7c10>", "forward": "<function ActorCriticPolicy.forward at 0x7fd3f59d7ca0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd3f59d7d30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd3f59d7dc0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd3f59d7e50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd3f59d7ee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd3f59d7f70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd3f59db040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fd3f59d26f0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677721838497600469, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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, "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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf33768ce6d2ddc9bae05af71d5931a37438856c9a6527db6d15966b73a8204d
+size 147319

ppo-LunarLander-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+1.7.0

ppo-LunarLander-v2/data

@@ -0,0 +1,95 @@
+{
+    "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 0x7fd3f59d79d0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd3f59d7a60>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd3f59d7af0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd3f59d7b80>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fd3f59d7c10>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fd3f59d7ca0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd3f59d7d30>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd3f59d7dc0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fd3f59d7e50>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd3f59d7ee0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd3f59d7f70>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd3f59db040>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fd3f59d26f0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            8
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 4,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1677721838497600469,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_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,
+    "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:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:170aa8f5e8fa14d9cc8e9b67252a29aa94c02ed0800a0363dd36dba98ff9c094
+size 87929

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4011328b6b4ce06cd24512603a98f764917c4f05e1d8f55b88b3bf5147e1a8f
+size 43393

ppo-LunarLander-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
+- Python: 3.8.10
+- Stable-Baselines3: 1.7.0
+- PyTorch: 1.13.1+cu116
+- GPU Enabled: True
+- Numpy: 1.22.4
+- Gym: 0.21.0

results.json

@@ -1 +1 @@
-{"mean_reward": -406.0670164668933, "std_reward": 108.38701740396247, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-02T01:46:55.717296"}
+{"mean_reward": 270.1763506196145, "std_reward": 19.099214642272532, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-02T02:20:20.233666"}