Commit
•
1b4c77a
1
Parent(s):
636a141
Upload
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +1 -1
- ppo-LunarLander-v2/data +18 -18
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 290.74 +/- 11.14
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +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 0x7a03b519b250>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a03b519b2e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a03b519b370>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a03b519b400>", "_build": "<function ActorCriticPolicy._build at 0x7a03b519b490>", "forward": "<function ActorCriticPolicy.forward at 0x7a03b519b520>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a03b519b5b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a03b519b640>", "_predict": "<function ActorCriticPolicy._predict at 0x7a03b519b6d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a03b519b760>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a03b519b7f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a03b519b880>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a03c292a980>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1702085946654557072, "learning_rate": 0.0001, "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": 1364, "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": 0.95, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 22, "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-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
|
|
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 0x7db5b028e680>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7db5b028e710>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7db5b028e7a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7db5b028e830>", "_build": "<function ActorCriticPolicy._build at 0x7db5b028e8c0>", "forward": "<function ActorCriticPolicy.forward at 0x7db5b028e950>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7db5b028e9e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7db5b028ea70>", "_predict": "<function ActorCriticPolicy._predict at 0x7db5b028eb00>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7db5b028eb90>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7db5b028ec20>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7db5b028ecb0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7db5bd9d4d80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1702091555007122672, "learning_rate": 0.0001, "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:": "gAWV6gsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHEUvhl18suMAWyUS/qMAXSUR0CxM8he9i+ddX2UKGgGR0Bv5kwHqu8saAdLvWgIR0CxNAbRWtEHdX2UKGgGR0Bz5ZoK2KEWaAdNBgFoCEdAsTQX114gR3V9lChoBkdAcfGnpjc2zmgHS9toCEdAsTRNCY1HfHV9lChoBkdAcWrQNCqp+GgHS/FoCEdAsTRNCZ4Oc3V9lChoBkdAcnjvPC2tuGgHS9FoCEdAsTS0txuKoHV9lChoBkdAcSguzhP0qmgHS7NoCEdAsTT4FC9h7XV9lChoBkdAcmJ/h2nsLWgHS8JoCEdAsTUDPTodMnV9lChoBkdAc8NBBiTdL2gHS/RoCEdAsTVJVYISlHV9lChoBkdAcPSE8aGYbGgHS8FoCEdAsTWyGj9GZ3V9lChoBkdAcscyWRigCmgHS91oCEdAsTXb6pHZsnV9lChoBkdAcIdpwCKaX2gHS79oCEdAsTXelchTwXV9lChoBkdAcjO1tO2y9mgHS8poCEdAsTXozEaVEHV9lChoBkdAcHEcpLEk0WgHS9poCEdAsTYNRekYXXV9lChoBkdAcX5U7jkuH2gHS81oCEdAsTYpAOavzXV9lChoBkdAcLDqv/zasmgHS9JoCEdAsTZtlpXZG3V9lChoBkdAcX6Ke05U+GgHS+ZoCEdAsTZygUUO/nV9lChoBkdAc5yLYPGyX2gHS9hoCEdAsTZ7CwbEP3V9lChoBkdAcD7Dbah6B2gHS7xoCEdAsTaOmDUVjHV9lChoBkdAcMn0knkT6GgHS9hoCEdAsTb3Nu+AVnV9lChoBkdAccuYgq3EymgHS+BoCEdAsTcTAEdNnHV9lChoBkdAcuiQJHAh0WgHS9poCEdAsTc4kdFOPHV9lChoBkdAcLaTWoWHlGgHS9ZoCEdAsTePC3w1BXV9lChoBkdAcCGBj4Hoo2gHS9NoCEdAsTe/t6X0G3V9lChoBkdAcPEB8hLXc2gHS9doCEdAsTe+11GLDXV9lChoBkdAcYzgDzRQamgHTXcCaAhHQLE3xJpnHvN1fZQoaAZHQGWdjopx3mpoB03oA2gIR0CxN+VC1JDmdX2UKGgGR0BwruEZiuuBaAdL22gIR0CxN+5UT+NtdX2UKGgGR0Bwfe5Yoy9FaAdLvWgIR0CxOBX2dupCdX2UKGgGR0B0UgBo24usaAdL5GgIR0CxOB5NO/L1dX2UKGgGR0B0N50aIeo2aAdLwGgIR0CxOC9ph4MXdX2UKGgGR0BzBVZ4fOlgaAdNEwFoCEdAsTg1UzbeuXV9lChoBkdAcp63974SH2gHS+9oCEdAsVFjC3w1BXV9lChoBkdAc55QWepXIWgHS/NoCEdAsVFuzE74jHV9lChoBkdAbj0lnh86WGgHS8BoCEdAsVGasLfDUHV9lChoBkdAc2FpDeCTU2gHS9FoCEdAsVGkaFVT73V9lChoBkdAcLzVlf7aZmgHS9loCEdAsVHj1Iy0r3V9lChoBkdAb52TFl05l2gHS8doCEdAsVI9wqAjIXV9lChoBkdAcq2B3zMA3mgHS+doCEdAsVJWrPt2LnV9lChoBkdAcK0cHGCI12gHS8FoCEdAsVJcUh3aBnV9lChoBkdAbWpe6Zpi7WgHS9poCEdAsVJrvgFX73V9lChoBkdAcyeAVfu1GGgHS+ZoCEdAsVJ+ScLBsXV9lChoBkdAcoW3AmAskWgHS91oCEdAsVKchnrY5HV9lChoBkdAbzGqSX+l02gHS9poCEdAsVK+gK4QSXV9lChoBkdAcXA3KSxJNGgHS9loCEdAsVLW8UVSGnV9lChoBkdAbmujua4MF2gHS9xoCEdAsVLjLeQ+2XV9lChoBkdAbjohOgxrSGgHS79oCEdAsVMs57w8XHV9lChoBkdAdG5WTot+TmgHS9VoCEdAsVNOcWj46HV9lChoBkdAcNnmEGqxT2gHS/VoCEdAsVNe1F6RhnV9lChoBkdAboG47Rv3rWgHS8FoCEdAsVPNp/PPcHV9lChoBkdAcLKtU4rBkGgHS+toCEdAsVPR/b0voXV9lChoBkdAcPyx+KCQLmgHS7doCEdAsVPW6tknTnV9lChoBkdAcgwM6RyOrGgHS8JoCEdAsVPpOnEVFnV9lChoBkdAcakFHrhR7GgHS7xoCEdAsVQFGBnSOXV9lChoBkdAcmRakyk9EGgHS75oCEdAsVQscFQl8nV9lChoBkdAcj9sCkoF3mgHS95oCEdAsVQ6Bg/kenV9lChoBkdAcllfvnbItGgHTYoBaAhHQLFUONqQA+91fZQoaAZHQG5dlIuoP09oB0vKaAhHQLFUYChN/ON1fZQoaAZHQGYC5Qgs9SxoB03oA2gIR0CxVH/NiYsvdX2UKGgGR0ByLlZr56+naAdL5mgIR0CxVKrVWjoIdX2UKGgGR0ByKhu2qkuZaAdL6WgIR0CxVLyFfzBidX2UKGgGR0Bxfkpx3mmtaAdLtmgIR0CxVM7CBPKudX2UKGgGR0ByVJG7SRbKaAdL2WgIR0CxVOKD9OyndX2UKGgGR0BzBKTFERapaAdL9WgIR0CxVTaS9ugpdX2UKGgGR0BwmgKG+K0laAdLzGgIR0CxVWGIfr8jdX2UKGgGR0ByRIXwb2lEaAdLyGgIR0CxVW2h24d7dX2UKGgGR0By7eHh0hePaAdL2mgIR0CxVXh7zCk5dX2UKGgGR0ByAHKmsNlRaAdL12gIR0CxVXnFUADJdX2UKGgGR0BwvMZAIIGAaAdLxGgIR0CxVX6PKdQPdX2UKGgGR0BwEi4oZydXaAdLzmgIR0CxVcS+L3sYdX2UKGgGR0ByPpq33HrAaAdL5WgIR0CxVfYkAxSHdX2UKGgGR0ByM7JeVs1saAdL4WgIR0CxVh3FcY65dX2UKGgGR0Byqrz6JqIraAdNCwFoCEdAsVY/F5v9+HV9lChoBkdAcE5WbgCOm2gHS8toCEdAsVZF3OfNA3V9lChoBkdAczpl41P3z2gHS/RoCEdAsVZr62v0RXV9lChoBkdAcIqGBnSOR2gHS9VoCEdAsVZuOLiuMnV9lChoBkdAceBDe0ojOmgHS9BoCEdAsVZ2APNFB3V9lChoBkdAc4I4vexfOWgHS/poCEdAsVbaii7Ci3V9lChoBkdAcE5d9Ujs2WgHS8BoCEdAsVcEQjD8+HV9lChoBkdAc6x+0w8GLWgHS+BoCEdAsVc9WxQizXV9lChoBkdAcqA+4smOVGgHS+JoCEdAsVdOqEOAiHV9lChoBkdAcdXWGyon8mgHS99oCEdAsVdOO3lS0nV9lChoBkdAc9ITSsr/bWgHTR0BaAhHQLFXfTYNAkd1fZQoaAZHQHHRJE2HclBoB0vjaAhHQLFXmlxOtXB1fZQoaAZHQHKrCxeLNwBoB0vfaAhHQLFXwamXPZ91fZQoaAZHQHBj/MB6rvNoB0vCaAhHQLFX9YEGJN11fZQoaAZHQHKgECNjsldoB0vnaAhHQLFX+BLwnYx1fZQoaAZHQHBEfeYUnG9oB0vGaAhHQLFYB4ecQRR1fZQoaAZHQHHCqaLGaQVoB0vqaAhHQLFYG0V8CxN1fZQoaAZHQHNrjGT9sJpoB0vdaAhHQLFYKUmD15B1fZQoaAZHQHIffustCiRoB00NAWgIR0CxWGR6jWTYdX2UKGgGR0BwFGr/82rGaAdLyWgIR0CxWHHjENvwdX2UKGgGR0Bz3UMZxaPkaAdL0WgIR0CxWK2tZFG5dX2UKGgGR0BwucV32VVxaAdLvWgIR0CxWM6fnOjZdX2UKGgGR0BzTTKKYRdyaAdL2WgIR0CxWPenIhhZdX2UKGgGR0BwgXzoUzsQaAdL22gIR0CxWQuLrHENdX2UKGgGR0Bu97q4YrJ9aAdLymgIR0CxWRoduHerdX2UKGgGR0BlOa+SKWLQaAdN6ANoCEdAsVlOxX4j8nV9lChoBkdAcs0XGff4y2gHS91oCEdAsVlemm+Cb3V9lChoBkdAcbbUF0PpZGgHS9ZoCEdAsVlypR4yGnVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1240, "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": 0.95, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 20, "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8aNuLrHEMthZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 147940
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:028c88762adbc6223c1f21ac16443727341b5106f4d9c9308934049477b99db7
|
3 |
size 147940
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,20 +4,20 @@
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__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 ",
|
7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
@@ -26,12 +26,12 @@
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
"learning_rate": 0.0001,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -45,13 +45,13 @@
|
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
-
":serialized:": "
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
-
"_n_updates":
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",
|
@@ -84,7 +84,7 @@
|
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
"batch_size": 64,
|
87 |
-
"n_epochs":
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
":serialized:": "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"
|
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__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 ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7db5b028e680>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7db5b028e710>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7db5b028e7a0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7db5b028e830>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7db5b028e8c0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7db5b028e950>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7db5b028e9e0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7db5b028ea70>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7db5b028eb00>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7db5b028eb90>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7db5b028ec20>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7db5b028ecb0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7db5bd9d4d80>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1702091555007122672,
|
30 |
"learning_rate": 0.0001,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
+
"_n_updates": 1240,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
|
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
"batch_size": 64,
|
87 |
+
"n_epochs": 20,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
":serialized:": "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"
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 88362
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b9d62108d3019651dbb3467da65622dffa9e40ab60fd41b043c3e5c04ee0605
|
3 |
size 88362
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e214d91d5506f14a0ac10bc7ac9bee5ac7c0a0f8b46b55f6d33d243bbb3aab9a
|
3 |
size 43762
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 290.7404378, "std_reward": 11.138733981570335, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-09T03:52:09.691968"}
|