maria-aguilera
commited on
Commit
•
4db87bf
1
Parent(s):
4d0329c
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 +94 -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: 241.36 +/- 43.08
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f18236085e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1823608670>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1823608700>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1823608790>", "_build": "<function ActorCriticPolicy._build at 0x7f1823608820>", "forward": "<function ActorCriticPolicy.forward at 0x7f18236088b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1823608940>", "_predict": "<function ActorCriticPolicy._predict at 0x7f18236089d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1823608a60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1823608af0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1823608b80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f18235fdf00>"}, "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": 1670631687964054660, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "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:dce43b78569c70403a469ad5936da1aef35ca125efab9de6d5b666d6c75bc514
|
3 |
+
size 147214
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.6.2
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f18236085e0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1823608670>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1823608700>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1823608790>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f1823608820>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f18236088b0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1823608940>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f18236089d0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1823608a60>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1823608af0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1823608b80>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f18235fdf00>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
+
"dtype": "float32",
|
27 |
+
"_shape": [
|
28 |
+
8
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1670631687964054660,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
|
56 |
+
},
|
57 |
+
"_last_obs": {
|
58 |
+
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
+
},
|
61 |
+
"_last_episode_starts": {
|
62 |
+
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.015808000000000044,
|
70 |
+
"ep_info_buffer": {
|
71 |
+
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 248,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.999,
|
81 |
+
"gae_lambda": 0.98,
|
82 |
+
"ent_coef": 0.01,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 4,
|
87 |
+
"clip_range": {
|
88 |
+
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "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"
|
90 |
+
},
|
91 |
+
"clip_range_vf": null,
|
92 |
+
"normalize_advantage": true,
|
93 |
+
"target_kl": null
|
94 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11251234c22f58074b5c7fd1a75cf68c3997961c9e9082e217185fb916de8be1
|
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:f85d97b18d30dc69504701a48350c8609ae9df51b341fcd78dcc8e212c0f1eaf
|
3 |
+
size 43201
|
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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
|
2 |
+
Python: 3.8.16
|
3 |
+
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.13.0+cu116
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (242 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 241.3639307059579, "std_reward": 43.084313248977466, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-10T00:46:55.215521"}
|