first push
Browse files- PPO-LunarLander-v2.zip +3 -0
- PPO-LunarLander-v2/_stable_baselines3_version +1 -0
- PPO-LunarLander-v2/data +99 -0
- PPO-LunarLander-v2/policy.optimizer.pth +3 -0
- PPO-LunarLander-v2/policy.pth +3 -0
- PPO-LunarLander-v2/pytorch_variables.pth +3 -0
- PPO-LunarLander-v2/system_info.txt +9 -0
- README.md +45 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
PPO-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1cb69595c87ca969a36336dd5a1777027fb53e3de3829157742c6a45738a055
|
3 |
+
size 146754
|
PPO-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
PPO-LunarLander-v2/data
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
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 0x786fba929120>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x786fba9291b0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x786fba929240>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x786fba9292d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x786fba929360>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x786fba9293f0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x786fba929480>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x786fba929510>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x786fba9295a0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x786fba929630>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x786fba9296c0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x786fba929750>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x786fba91fc80>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 1015808,
|
25 |
+
"_total_timesteps": 1000000,
|
26 |
+
"_num_timesteps_at_start": 0,
|
27 |
+
"seed": null,
|
28 |
+
"action_noise": null,
|
29 |
+
"start_time": 1691417432587568972,
|
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'>",
|
38 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
39 |
+
},
|
40 |
+
"_last_original_obs": null,
|
41 |
+
"_episode_num": 0,
|
42 |
+
"use_sde": false,
|
43 |
+
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.015808000000000044,
|
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": 248,
|
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]",
|
61 |
+
"_shape": [
|
62 |
+
8
|
63 |
+
],
|
64 |
+
"low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
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": null
|
69 |
+
},
|
70 |
+
"action_space": {
|
71 |
+
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
+
"n": "4",
|
74 |
+
"start": "0",
|
75 |
+
"_shape": [],
|
76 |
+
"dtype": "int64",
|
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
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a676467cbb2859bd2c1fbbe3bfc7ec0724bd9bc232887014b8e4ce4475db83d
|
3 |
+
size 87929
|
PPO-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ea3d2f08d1f80473d5b7691f64e1c2c79930d7a50a126ad2fae2871d55af622
|
3 |
+
size 43329
|
PPO-LunarLander-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
PPO-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
|
2 |
+
- Python: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.0.1+cu118
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
README.md
CHANGED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- LunarLander-v2
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: PPO
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: LunarLander-v2
|
16 |
+
type: LunarLander-v2
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 244.16 +/- 18.09
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **PPO** Agent playing **LunarLander-v2**
|
25 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
26 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
+
|
28 |
+
## Usage (with Stable-baselines3)
|
29 |
+
|
30 |
+
```python
|
31 |
+
from stable_baselines3 import PPO
|
32 |
+
from stable_baselines3.common.monitor import Monitor
|
33 |
+
from huggingface_sb3 import load_from_hub
|
34 |
+
|
35 |
+
repo_id = "helamri/PPO-LunarLander-v2"
|
36 |
+
filename = "PPO-LunarLander-v2.zip"
|
37 |
+
|
38 |
+
checkpoint = load_from_hub(repo_id, filename)
|
39 |
+
model = PPO.load(checkpoint, print_system_info=True)
|
40 |
+
|
41 |
+
eval_env = Monitor(gym.make("LunarLander-v2", render_mode="human"))
|
42 |
+
|
43 |
+
mean_rwd, std_rwd = evaluate_policy(model, eval_env, n_eval_episodes=10)
|
44 |
+
print(f"mean_reward: {mean_rwd}±{std_rwd}")
|
45 |
+
```
|
config.json
ADDED
@@ -0,0 +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 0x786fba929120>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x786fba9291b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x786fba929240>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x786fba9292d0>", "_build": "<function ActorCriticPolicy._build at 0x786fba929360>", "forward": "<function ActorCriticPolicy.forward at 0x786fba9293f0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x786fba929480>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x786fba929510>", "_predict": "<function ActorCriticPolicy._predict at 0x786fba9295a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x786fba929630>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x786fba9296c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x786fba929750>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x786fba91fc80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1691417432587568972, "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:": "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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-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 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"}}
|
replay.mp4
ADDED
Binary file (179 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 244.15573720000003, "std_reward": 18.08878985884901, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-07T14:41:53.737577"}
|