taehoon1lee
commited on
Commit
·
2f8096e
1
Parent(s):
34c4d86
4th
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +24 -24
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +2 -2
- ppo-LunarLander-v2/system_info.txt +5 -5
- 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: -772.57 +/- 489.35
|
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 0x7ff13b344820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff13b3448b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff13b344940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff13b3449d0>", "_build": "<function ActorCriticPolicy._build at 0x7ff13b344a60>", "forward": "<function ActorCriticPolicy.forward at 0x7ff13b344af0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff13b344b80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff13b344c10>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff13b344ca0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff13b344d30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff13b344dc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff13b344e50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ff13b342f40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2523136, "_total_timesteps": 2500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1688190399184307486, "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": -0.009254400000000107, "_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": 308, "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": 2048, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "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-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "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 0x7f0806e00a60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0806e00af0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0806e00b80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0806e00c10>", "_build": "<function ActorCriticPolicy._build at 0x7f0806e00ca0>", "forward": "<function ActorCriticPolicy.forward at 0x7f0806e00d30>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f0806e00dc0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0806e00e50>", "_predict": "<function ActorCriticPolicy._predict at 0x7f0806e00ee0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0806e00f70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0806e03040>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0806e030d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f0806e7e4e0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 16384, "_total_timesteps": 100, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1690722213996335373, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAFp4Tz7jaHg/PiJHP1nCab/dY8y+uuy6vgAAAAAAAAAAAOjDvKy6tD8ciEC+zpPqu/Rwmbwwktm9AAAAAAAAAACzamk9u6KuPyTwCj6quqW+0e6uveMJOL4AAAAAAAAAAOa/bT3BbqQ/niy8PlSv3r78eaO9Cl3KvAAAAAAAAAAAs9hEPS9a1z8i6gA+i/4EPS2gjb0Cnz+9AAAAAAAAAABmDrI74pu8P6TsjD1qWTQ+xEJBvXeHA74AAAAAAAAAAIDwSr4ynnk/AeMHv5G0PL/p+rI++MC1PgAAAAAAAAAAJoDCvQYhnj8kU5O+vckJv17aej7jhbE9AAAAAAAAAABmNug7YHa8P+Mr3j0i+Y2+lDzavm3Vzb4AAAAAAAAAAP2ixT649gk/c9x2P1yJgr85/gO/FRg2vgAAAAAAAAAA+l/Rvp62xT2RYAG/Ch2FvipqCkCi5B5AAAAAAAAAAADNDfK8YZG0P5bI+r6Gxa28mL5IPA0AGToAAAAAAAAAAGAIUz4LIhc/mlILP7WpkL/ahmS/DWTqvgAAAAAAAAAAulQUPj4LND+fTwE/gheGv3Nzer70zz6+AAAAAAAAAAAzG6Y7PqHJP441SjwPb4Q9odbbvdMn0r0AAAAAAAAAALI6kL4I3MI+h5YdvwJbn7+/D9w+MiGXvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_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": -162.84, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwHbmWmYSg5CMAWyUS1yMAXSUR0At4BEKE385dX2UKGgGR8BTY+Aqd6LPaAdLe2gIR0At60SAYpDvdX2UKGgGR8B369eVs1sMaAdLaGgIR0AuBkLhJiAldX2UKGgGR8BkKNjwx33YaAdLQmgIR0AuBQdjoZAIdX2UKGgGR8BnE5VuJk5IaAdLZmgIR0AuFvwVj7Q+dX2UKGgGR8Bj2RTZQHiWaAdLZWgIR0AuHcTrVvuPdX2UKGgGR8BnKjK7qY7aaAdLVWgIR0AuMFTNt65YdX2UKGgGR8BSbU4FRpDeaAdLO2gIR0AuTHJ9y926dX2UKGgGR8B1NEq/dqL1aAdLgGgIR0AudLCemNzbdX2UKGgGR8BWOWKyfL9uaAdLQ2gIR0AudFlTWGypdX2UKGgGR8BhkfryDqW1aAdLZmgIR0AudtKqXF98dX2UKGgGR8BXd4eT3Zf2aAdLT2gIR0AufWdVea8ZdX2UKGgGR8Bp8J+F10T2aAdLUWgIR0AugI3zcynDdX2UKGgGR8B7rN07r9l3aAdLbmgIR0AuhxyXD3uedX2UKGgGR8Bx67V7Qb++aAdLVmgIR0AukXP7el9CdX2UKGgGR8BiJ8Z9/jKgaAdLXmgIR0Auk25QP7N0dX2UKGgGR8A5fPY4ACGOaAdLZWgIR0Aup4+r2g3+dX2UKGgGR8BhVuALApKBaAdLRmgIR0AurVBlcyFgdX2UKGgGR8BtYIYP5HmSaAdLVmgIR0Aut8PWhAW0dX2UKGgGR8BTSA6ySmqHaAdLV2gIR0AuzU6xPfsNdX2UKGgGR8BZDeObRWtEaAdLfWgIR0Au2uIyj59FdX2UKGgGR8Be0nRXwLE2aAdLVmgIR0AvC3XI2fkFdX2UKGgGR8Bko/EAHVwxaAdLQWgIR0AvCwosqaw2dX2UKGgGR8B590tnPE88aAdLemgIR0AvD9lVcUuddX2UKGgGR8BRM37cfvF4aAdLRGgIR0AvF6Tnq3VkdX2UKGgGR8BeZ3jABT4taAdLSWgIR0AvIx9oexOddX2UKGgGR8B3m20qpcX4aAdLdmgIR0AvPgLJCBwudX2UKGgGR8B14x8zAN5MaAdLVWgIR0AvYhEBsANodX2UKGgGR8BWyH9vS+g2aAdLZ2gIR0AvejWTX8O1dX2UKGgGR8BvZYEt/WlNaAdLamgIR0AvedIXj2i+dX2UKGgGR8B06nZTQ3PzaAdLaWgIR0Avi/FirksCdX2UKGgGR8BpzMjLSuyNaAdLWGgIR0AvjXuE25xzdX2UKGgGR8BjVCeumrKeaAdLdGgIR0AvjXxvvSc9dX2UKGgGR8BXONkJ8fFKaAdLTWgIR0Avinm7rcCYdX2UKGgGR8BqtaLhrFfiaAdLZ2gIR0AvnjJ+2E00dX2UKGgGR8BXvO+IuXeFaAdLSWgIR0AvswkgOjIrdX2UKGgGR8BUgd/OMVDbaAdLSmgIR0Avv9zfaYeDdX2UKGgGR8BYuddu5z5oaAdLfmgIR0Avybm2b5M2dX2UKGgGR8BvzpI+W4ViaAdLWGgIR0Avz8D0UXYUdX2UKGgGR8B2B/QiRnvlaAdLXWgIR0Av3Hd43WFwdX2UKGgGR8BgDLHXEqDsaAdLdGgIR0Av5s0pEx7BdX2UKGgGR8Bt5YBzV+ZxaAdLZ2gIR0Av+ORT0g8sdX2UKGgGR8Bir8QwsXizaAdLXWgIR0AwAnOSntOVdX2UKGgGR8BiQ/mxMWXUaAdLU2gIR0AwCLHdXT3JdX2UKGgGR8Bein9rGipOaAdLQ2gIR0AwCkrPMSsbdX2UKGgGR8BdxXfQ8fV7aAdLU2gIR0AwEnV5KODKdX2UKGgGR8BWvQVj7Q9iaAdLQGgIR0AwHIAOrhitdX2UKGgGR8BcxK2WpqASaAdLXmgIR0AwJbqhUR4AdX2UKGgGR8B56VO6/ZdwaAdLaWgIR0AwKa0hNdqtdX2UKGgGR8BgPLdi2DxtaAdLeGgIR0AwQHGS6lLwdX2UKGgGR8BgsjCxeLNwaAdLcGgIR0AwQ1PFefI0dX2UKGgGR8BYNQq3EyckaAdLQ2gIR0AwRf5DZ13ddX2UKGgGR8By28ikfs/qaAdLYWgIR0AwTLuhK15TdX2UKGgGR8B1dh0eU6geaAdLhWgIR0AwT7oB7u2JdX2UKGgGR8Bgadkc0cfeaAdLX2gIR0AwUS7oSteVdX2UKGgGR8Bbkd8qnWJ8aAdLYmgIR0AwWEYwZflZdX2UKGgGR8B1ygOEug6EaAdLcmgIR0AwW1Q66reZdX2UKGgGR8Bgp9waR6njaAdLWWgIR0AwY1QqI7/5dX2UKGgGR8BSwvXXiBGyaAdLQGgIR0AwaLq2SdOJdX2UKGgGR8BRUCl3yI56aAdLT2gIR0Awb4vN/vv0dX2UKGgGR8B2LZ5hScbzaAdLZGgIR0AwcYRujynUdX2UKGgGR8BZpMKCxu89aAdLWmgIR0AwcPzFuNxVdX2UKGgGR8BCg5qubI91aAdLlGgIR0AweqMFUyYYdX2UKGgGR8BbetVrAP/aaAdLfmgIR0AwfRkVeruIdX2UKGgGR8BbOovvjOs1aAdLPWgIR0Awg+717IDHdX2UKGgGR8Bcgh/y5I6KaAdLWWgIR0AwhKHwgDA8dX2UKGgGR8BdtrY9Pk7waAdLRGgIR0AwkuAZsKsudX2UKGgGR8Bc9aUmlZX/aAdLUWgIR0Awk287IT4+dX2UKGgGR8BR01fJFLFoaAdLSGgIR0AwksvqTr3TdX2UKGgGR8Bo4J2B8QZoaAdLWGgIR0AwmAjY7JXAdX2UKGgGR8BJHSOaOPvKaAdLQWgIR0AwrmZVn27GdX2UKGgGR8B2hjZQHiWFaAdLXmgIR0AwtI1tO2y+dX2UKGgGR8BYTRHoX9BKaAdLRmgIR0Aws7ulXRw7dX2UKGgGR8BtCyW3Sa3JaAdLamgIR0AwuE7GNrCWdX2UKGgGR8BvvieCkGiYaAdLZGgIR0AwvncL0BfbdX2UKGgGR8BYa7kbPyCnaAdLWmgIR0AwwSOinHeadX2UKGgGR8BpnYYLsruqaAdLVGgIR0AwwYrrgOz6dX2UKGgGR8Bd0nLmp2lmaAdLbGgIR0AwzmtyPuG9dX2UKGgGR8BKjvY4ACGOaAdLP2gIR0Aw01ZkkKNRdX2UKGgGR8BgU+wcHWz4aAdLVmgIR0Aw2hfBvaUSdX2UKGgGR8BjPZnrY5DJaAdLQ2gIR0Aw3S2H+IdmdX2UKGgGR8Bu+gXoC+10aAdLbGgIR0Aw6Ca7VawEdX2UKGgGR8BnBcifQKKHaAdLbmgIR0Aw85jYqXnhdX2UKGgGR8BgVJ4nndO7aAdLYmgIR0Aw+BBAv+OwdX2UKGgGR8BhOrl1bJOnaAdLe2gIR0Aw9d+5OJtSdX2UKGgGR8BX4NR77bcoaAdLT2gIR0AxAFA3T/hmdX2UKGgGR8BX4JUkv9LpaAdLUGgIR0AxCJ53Tuv2dX2UKGgGR8Bc57QTmGM5aAdLWmgIR0AxDjW07bL2dX2UKGgGR8BgWck0Jng6aAdLPmgIR0AxD2H+IdlvdX2UKGgGR8Bg+T2WY4Q0aAdLX2gIR0AxEkNnXd0rdX2UKGgGR8BZ94FJQLuyaAdLVmgIR0AxFmvnr6cidX2UKGgGR8BXfcghbGFSaAdLgmgIR0AxFmuDBdledX2UKGgGR8BiBumBOHnEaAdLY2gIR0AxIBoVVPvbdX2UKGgGR8BepKqGUOd5aAdLOmgIR0AxH/82rGR3dX2UKGgGR8BzWZSzgMtsaAdLWWgIR0AxJh8YyfthdX2UKGgGR8BykEFxGUfQaAdLbWgIR0AxLY2Kl54XdX2UKGgGR8Bv8PuAqd6LaAdLXmgIR0AxOzUqhDgJdX2UKGgGR8BZ0fR7Z39raAdLSWgIR0AxQM/QjUutdX2UKGgGR8BX3yhzvJA/aAdLZmgIR0AxQZqmCROldX2UKGgGR8BBA33QD3dsaAdLUWgIR0AxRUyHmA9WdWUu"}, "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:": "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-5.15.90.1-microsoft-standard-WSL2-x86_64-with-glibc2.29 # 1 SMP Fri Jan 27 02:56:13 UTC 2023", "Python": "3.8.10", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.3", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcb457324c4954ecccc7508303fd8c1e3f2f16b6681f86463908881c7c1999a8
|
3 |
+
size 146107
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,34 +4,34 @@
|
|
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": "<
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
-
"num_timesteps":
|
25 |
-
"_total_timesteps":
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -41,17 +41,17 @@
|
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
-
"_current_progress_remaining": -
|
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:": "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",
|
@@ -77,23 +77,23 @@
|
|
77 |
"_np_random": null
|
78 |
},
|
79 |
"n_envs": 16,
|
80 |
-
"n_steps":
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
-
"batch_size":
|
87 |
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
-
":serialized:": "
|
91 |
},
|
92 |
"clip_range_vf": null,
|
93 |
"normalize_advantage": true,
|
94 |
"target_kl": null,
|
95 |
"lr_schedule": {
|
96 |
":type:": "<class 'function'>",
|
97 |
-
":serialized:": "
|
98 |
}
|
99 |
}
|
|
|
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 0x7f0806e00a60>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0806e00af0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0806e00b80>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0806e00c10>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f0806e00ca0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f0806e00d30>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f0806e00dc0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0806e00e50>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f0806e00ee0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0806e00f70>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0806e03040>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0806e030d0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f0806e7e4e0>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 16384,
|
25 |
+
"_total_timesteps": 100,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1690722213996335373,
|
30 |
"learning_rate": 0.0003,
|
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'>",
|
|
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -162.84,
|
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": 4,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",
|
|
|
77 |
"_np_random": null
|
78 |
},
|
79 |
"n_envs": 16,
|
80 |
+
"n_steps": 1024,
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "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"
|
91 |
},
|
92 |
"clip_range_vf": null,
|
93 |
"normalize_advantage": true,
|
94 |
"target_kl": null,
|
95 |
"lr_schedule": {
|
96 |
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "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"
|
98 |
}
|
99 |
}
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34e6dfabb88978d3ca0f816a6c4b10782bef1600479fbe20c116beb456c32029
|
3 |
+
size 87545
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2180e1bfac9573934d83f058b534ae8ece05aa0b6c57bbc7440451954b26d84d
|
3 |
+
size 43201
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
-
- OS: Linux-5.15.
|
2 |
-
- Python: 3.10
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
-
- PyTorch: 2.0.1+
|
5 |
- GPU Enabled: True
|
6 |
-
- Numpy: 1.
|
7 |
- Cloudpickle: 2.2.1
|
8 |
- Gymnasium: 0.28.1
|
9 |
-
- OpenAI Gym: 0.
|
|
|
1 |
+
- OS: Linux-5.15.90.1-microsoft-standard-WSL2-x86_64-with-glibc2.29 # 1 SMP Fri Jan 27 02:56:13 UTC 2023
|
2 |
+
- Python: 3.8.10
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.0.1+cu117
|
5 |
- GPU Enabled: True
|
6 |
+
- Numpy: 1.24.3
|
7 |
- Cloudpickle: 2.2.1
|
8 |
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.26.2
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": -772.5670782999999, "std_reward": 489.3488293149174, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-30T13:05:36.865594"}
|