Commit
•
a693561
1
Parent(s):
7d6b8b8
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +27 -27
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +2 -2
- ppo-LunarLander-v2/system_info.txt +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: 280.05 +/- 13.09
|
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 0x7ac00dd4bd00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ac00dd4bd90>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ac00dd4be20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ac00dd4beb0>", "_build": "<function ActorCriticPolicy._build at 0x7ac00dd4bf40>", "forward": "<function ActorCriticPolicy.forward at 0x7ac00db58040>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ac00db580d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ac00db58160>", "_predict": "<function ActorCriticPolicy._predict at 0x7ac00db581f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ac00db58280>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ac00db58310>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ac00db583a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ac00dce7080>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1716859433585555128, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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 0x7b143616c4c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b143616c550>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b143616c5e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b143616c670>", "_build": "<function ActorCriticPolicy._build at 0x7b143616c700>", "forward": "<function ActorCriticPolicy.forward at 0x7b143616c790>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b143616c820>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b143616c8b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7b143616c940>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b143616c9d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b143616ca60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b143616caf0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b1436116900>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1503232, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1716917051098470062, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAIAlN77+rSU/Xm4hPlcxmL4WWLO8NWnePAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.002154666666666749, "_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": 1468, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVOgMAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlIwUbnVtcHkucmFuZG9tLl9waWNrbGWUjBBfX2dlbmVyYXRvcl9jdG9ylJOUjAVQQ0c2NJRoMowUX19iaXRfZ2VuZXJhdG9yX2N0b3KUk5SGlFKUfZQojA1iaXRfZ2VuZXJhdG9ylIwFUENHNjSUjAVzdGF0ZZR9lChoPYoQ2ezKp4ODzrtuWAJA3C9/UYwDaW5jlIoRDSxc+wY4VeAl/dGVhSs2uwB1jApoYXNfdWludDMylEsAjAh1aW50ZWdlcpRLAHVidWIu", "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": "Generator(PCG64)"}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWVpAEAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlIwUbnVtcHkucmFuZG9tLl9waWNrbGWUjBBfX2dlbmVyYXRvcl9jdG9ylJOUjAVQQ0c2NJRoG4wUX19iaXRfZ2VuZXJhdG9yX2N0b3KUk5SGlFKUfZQojA1iaXRfZ2VuZXJhdG9ylIwFUENHNjSUjAVzdGF0ZZR9lChoJooRV84T7Me/Lu0146La3HVHhgCMA2luY5SKEPlJNNomPa7CHLnQZx/ajnF1jApoYXNfdWludDMylEsBjAh1aW50ZWdlcpSKBbGWWJsAdWJ1Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "n_steps": 4096, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cu121", "GPU Enabled": "False", "Numpy": "1.25.2", "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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:925a38874e39778db012a607aa42e59e6125f6682c3a4dbe7bbc40c1dfe5f216
|
3 |
+
size 147381
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,57 +4,57 @@
|
|
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": {},
|
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'>",
|
38 |
-
":serialized:": "
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
-
"_current_progress_remaining": -0.
|
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:": "
|
58 |
"dtype": "float32",
|
59 |
"bounded_below": "[ True True True True True True True True]",
|
60 |
"bounded_above": "[ True True True True True True True True]",
|
@@ -65,19 +65,19 @@
|
|
65 |
"high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
66 |
"low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
67 |
"high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
68 |
-
"_np_random":
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
-
":serialized:": "
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
76 |
"dtype": "int64",
|
77 |
-
"_np_random":
|
78 |
},
|
79 |
-
"n_envs":
|
80 |
-
"n_steps":
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
83 |
"ent_coef": 0.01,
|
|
|
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 0x7b143616c4c0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b143616c550>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b143616c5e0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b143616c670>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7b143616c700>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7b143616c790>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7b143616c820>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b143616c8b0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7b143616c940>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b143616c9d0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b143616ca60>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7b143616caf0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7b1436116900>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 1503232,
|
25 |
+
"_total_timesteps": 1500000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1716917051098470062,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAIAlN77+rSU/Xm4hPlcxmL4WWLO8NWnePAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.002154666666666749,
|
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": 1468,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
+
":serialized:": "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",
|
58 |
"dtype": "float32",
|
59 |
"bounded_below": "[ True True True True True True True True]",
|
60 |
"bounded_above": "[ True True True True True True True True]",
|
|
|
65 |
"high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
66 |
"low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
67 |
"high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
68 |
+
"_np_random": "Generator(PCG64)"
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "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",
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
76 |
"dtype": "int64",
|
77 |
+
"_np_random": "Generator(PCG64)"
|
78 |
},
|
79 |
+
"n_envs": 1,
|
80 |
+
"n_steps": 4096,
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
83 |
"ent_coef": 0.01,
|
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 sha256:46a562ff5a3ee4c08db81970467b04f916d5456e434a844bcef62a37fb2739fc
|
3 |
+
size 87978
|
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:ebf8f1f08050b2006665dfb3fd22a2799a78e776b06ff4db51a8f01a273a1e53
|
3 |
+
size 43634
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
- PyTorch: 2.3.0+cu121
|
5 |
-
- GPU Enabled:
|
6 |
- Numpy: 1.25.2
|
7 |
- Cloudpickle: 2.2.1
|
8 |
- Gymnasium: 0.28.1
|
|
|
2 |
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
- PyTorch: 2.3.0+cu121
|
5 |
+
- GPU Enabled: False
|
6 |
- Numpy: 1.25.2
|
7 |
- Cloudpickle: 2.2.1
|
8 |
- Gymnasium: 0.28.1
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 280.05293689999996, "std_reward": 13.092630536653711, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-28T18:04:55.589163"}
|