Upload from RL course

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -300.05 +/- 226.13
+      value: 243.42 +/- 16.88
       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 0x7f16c8ad0430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f16c8ad04c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f16c8ad0550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f16c8ad05e0>", "_build": "<function ActorCriticPolicy._build at 0x7f16c8ad0670>", "forward": "<function ActorCriticPolicy.forward at 0x7f16c8ad0700>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f16c8ad0790>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f16c8ad0820>", "_predict": "<function ActorCriticPolicy._predict at 0x7f16c8ad08b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f16c8ad0940>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f16c8ad09d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f16c8ad0a60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f160430d440>"}, "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:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "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-5.15.0-102-generic-x86_64-with-glibc2.35 # 112-Ubuntu SMP Tue Mar 5 16:50:32 UTC 2024", "Python": "3.10.0", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.2", "GPU Enabled": "True", "Numpy": "1.24.3", "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 0x7f16c8ad0430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f16c8ad04c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f16c8ad0550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f16c8ad05e0>", "_build": "<function ActorCriticPolicy._build at 0x7f16c8ad0670>", "forward": "<function ActorCriticPolicy.forward at 0x7f16c8ad0700>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f16c8ad0790>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f16c8ad0820>", "_predict": "<function ActorCriticPolicy._predict at 0x7f16c8ad08b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f16c8ad0940>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f16c8ad09d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f16c8ad0a60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f160430d440>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1712836531998946685, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "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:": "gAWV5AIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMZy9ob21lL2RhbGxvbmYvZGV2cm9vdC9odWdnaW5nZmFjZV9ybC9lbnYvbGliL3B5dGhvbjMuMTAvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjGcvaG9tZS9kYWxsb25mL2RldnJvb3QvaHVnZ2luZ2ZhY2VfcmwvZW52L2xpYi9weXRob24zLjEwL3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUaACMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.0-102-generic-x86_64-with-glibc2.35 # 112-Ubuntu SMP Tue Mar 5 16:50:32 UTC 2024", "Python": "3.10.0", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.2", "GPU Enabled": "True", "Numpy": "1.24.3", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90b43f931e0de5e35077d303b833a7adce0e3d64a29388526e18afb57d58fcef
-size 55225
+oid sha256:b02aab9460c7d81750c5835b927ff0607eb401480e7a0711c3c252b366f47f81
+size 148152

ppo-LunarLander-v2/data

@@ -21,25 +21,37 @@
     },
     "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": 1712836531998946685,
     "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:af3566ec7268c9315a653931fb479281e2b857f83d72fe91514d076766d2786b
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab6e70c67d792119f1075c6526f632eac76036aa451f43b85120281a0e9eb7b2
+oid sha256:4266a442f09bad5cdb30d73b65ead743cdaa73cef02082a1dda3ee9757d5c203
 size 43762

ppo-LunarLander-v2/system_info.txt

@@ -6,3 +6,4 @@
 - Numpy: 1.24.3
 - Cloudpickle: 3.0.0
 - Gymnasium: 0.28.1
+- OpenAI Gym: 0.26.2

results.json

@@ -1 +1 @@
-{"mean_reward": -300.04783729999997, "std_reward": 226.131093763628, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-11T11:41:55.281583"}
+{"mean_reward": 243.4200154, "std_reward": 16.87834321533977, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-11T16:13:22.504995"}