juanmi1234
commited on
Commit
•
e9df6df
1
Parent(s):
5cf6d7e
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +37 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +95 -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 +7 -0
- replay.mp4 +0 -0
- results.json +1 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 277.23 +/- 20.26
|
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 |
+
TODO: Add your code
|
30 |
+
|
31 |
+
|
32 |
+
```python
|
33 |
+
from stable_baselines3 import ...
|
34 |
+
from huggingface_sb3 import load_from_hub
|
35 |
+
|
36 |
+
...
|
37 |
+
```
|
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 0x7fc27f179700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc27f179790>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc27f179820>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc27f1798b0>", "_build": "<function ActorCriticPolicy._build at 0x7fc27f179940>", "forward": "<function ActorCriticPolicy.forward at 0x7fc27f1799d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc27f179a60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc27f179af0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc27f179b80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc27f179c10>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc27f179ca0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc27f179d30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fc27f178c80>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1680052881878252289, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:330e3918340b939d5a12012a28b382fb7c373349ba42965e4d9b784d02fdf1ab
|
3 |
+
size 147377
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7fc27f179700>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc27f179790>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc27f179820>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc27f1798b0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fc27f179940>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fc27f1799d0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc27f179a60>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc27f179af0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fc27f179b80>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc27f179c10>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc27f179ca0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc27f179d30>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7fc27f178c80>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"observation_space": {
|
25 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
26 |
+
":serialized:": "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",
|
27 |
+
"dtype": "float32",
|
28 |
+
"_shape": [
|
29 |
+
8
|
30 |
+
],
|
31 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
32 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
33 |
+
"bounded_below": "[False False False False False False False False]",
|
34 |
+
"bounded_above": "[False False False False False False False False]",
|
35 |
+
"_np_random": null
|
36 |
+
},
|
37 |
+
"action_space": {
|
38 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
39 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
40 |
+
"n": 4,
|
41 |
+
"_shape": [],
|
42 |
+
"dtype": "int64",
|
43 |
+
"_np_random": null
|
44 |
+
},
|
45 |
+
"n_envs": 16,
|
46 |
+
"num_timesteps": 1015808,
|
47 |
+
"_total_timesteps": 1000000,
|
48 |
+
"_num_timesteps_at_start": 0,
|
49 |
+
"seed": null,
|
50 |
+
"action_noise": null,
|
51 |
+
"start_time": 1680052881878252289,
|
52 |
+
"learning_rate": 0.0003,
|
53 |
+
"tensorboard_log": null,
|
54 |
+
"lr_schedule": {
|
55 |
+
":type:": "<class 'function'>",
|
56 |
+
":serialized:": "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"
|
57 |
+
},
|
58 |
+
"_last_obs": {
|
59 |
+
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAM1sBj1SgPm5WWyVMjFyTLDjtMM6v6oPswAAgD8AAIA/QH/cvbWMrT+Rux2/GuG0vl77jb1wmJe+AAAAAAAAAADNfC0+KrlmPna5P75pNJm+k5BqvY5UFr0AAAAAAAAAAEBar72944w/QiM6vi+9F7+QAdy9lbKmPAAAAAAAAAAA5toZPbogpz8rEig+aEUAvwaoLj3tly67AAAAAAAAAAAgAR8+oVUKP/qvXb6gucC+4r/NOrGdFr4AAAAAAAAAALNL2j2+wpw9apAtvnNNir72G4e9WkSjOwAAAAAAAAAAmvmuu9vqhbwC3+A93HYkPXro6r1/NwA+AACAPwAAgD/tJim+XNmSPiReNj5wb4K+Cn1mvU92nT0AAAAAAAAAALMp6D3I3R4/JjPQvXNXqb7/JzI9qPS2vQAAAAAAAAAAGhqzPUg9krrb06G5JNOmNKZ0GLu3mcM4AACAPwAAgD8N7Ns9LFtkP+B2pDs9w9a+7cYrPsZKhb0AAAAAAAAAADNcRT1qONM+DNMtvT8jur544Li8yndIvQAAAAAAAAAAMyUsPXv+trra+B42iTozMeCpBDqGCkK1AACAPwAAgD/NUNI7Uui7uWRTRLQNvAIwxbfUu8+CkjMAAIA/AACAP7OHxz2QDbw/o2jBPhRQXr61J+g9Wv30PQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
|
61 |
+
},
|
62 |
+
"_last_episode_starts": {
|
63 |
+
":type:": "<class 'numpy.ndarray'>",
|
64 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
65 |
+
},
|
66 |
+
"_last_original_obs": null,
|
67 |
+
"_episode_num": 0,
|
68 |
+
"use_sde": false,
|
69 |
+
"sde_sample_freq": -1,
|
70 |
+
"_current_progress_remaining": -0.015808000000000044,
|
71 |
+
"ep_info_buffer": {
|
72 |
+
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "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"
|
74 |
+
},
|
75 |
+
"ep_success_buffer": {
|
76 |
+
":type:": "<class 'collections.deque'>",
|
77 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
+
},
|
79 |
+
"_n_updates": 248,
|
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 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b4aa00a938cf4d5bbe20f3f73e4a3716c7605395262164885b5ffd15fca97ca
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54bffb02ddac49677c3853d85822fe7ad6ef78b036ae5428d6594360098637de
|
3 |
+
size 43393
|
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 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.9.16
|
3 |
+
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.1+cu116
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (221 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 277.2260521077164, "std_reward": 20.25840288652351, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-29T01:52:10.348135"}
|