Francois2511
commited on
Commit
•
0b3c985
1
Parent(s):
7af9d62
ADD unit1 model
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: 241.61 +/- 22.12
|
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 0x7f728dd8bb80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f728dd8bc10>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f728dd8bca0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f728dd8bd30>", "_build": "<function ActorCriticPolicy._build at 0x7f728dd8bdc0>", "forward": "<function ActorCriticPolicy.forward at 0x7f728dd8be50>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f728dd8bee0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f728dd8bf70>", "_predict": "<function ActorCriticPolicy._predict at 0x7f728dd90040>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f728dd900d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f728dd90160>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f728dd901f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f728dd81fc0>"}, "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": 1678229105521525873, "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-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "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:d764bb495f77505e6f1c0b6f7b9b1b136e888f69c17b1dbe8d97ae88dc8ebb5e
|
3 |
+
size 147420
|
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 0x7f728dd8bb80>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f728dd8bc10>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f728dd8bca0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f728dd8bd30>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f728dd8bdc0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f728dd8be50>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f728dd8bee0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f728dd8bf70>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f728dd90040>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f728dd900d0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f728dd90160>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f728dd901f0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f728dd81fc0>"
|
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": 1678229105521525873,
|
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:": "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"
|
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:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
|
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 sha256:5776c6539409947eca13241f912683569d232a93fc52379712a532e0df090b63
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76f34e3c305a92d9393b0e00a6027a8a76ad0d741ba98402f85649b484ff4a68
|
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-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.8.10
|
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 (234 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 241.61098942089023, "std_reward": 22.11696422260028, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-07T23:10:52.895069"}
|