ZhihongDeng
commited on
Commit
·
1167b43
1
Parent(s):
35a52b5
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: 252.87 +/- 20.63
|
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 0x7f17b2c4cdc0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f17b2c4ce50>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f17b2c4cee0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f17b2c4cf70>", "_build": "<function ActorCriticPolicy._build at 0x7f17b2bd0040>", "forward": "<function ActorCriticPolicy.forward at 0x7f17b2bd00d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f17b2bd0160>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f17b2bd01f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f17b2bd0280>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f17b2bd0310>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f17b2bd03a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f17b2bd0430>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f17b2c4b3c0>"}, "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": 1676540042526176185, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "_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": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:776be4277cee4ff982b1f4a7667fb92d79671a3f4939466f4e6090c472ae4244
|
3 |
+
size 147424
|
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 0x7f17b2c4cdc0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f17b2c4ce50>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f17b2c4cee0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f17b2c4cf70>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f17b2bd0040>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f17b2bd00d0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f17b2bd0160>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f17b2bd01f0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f17b2bd0280>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f17b2bd0310>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f17b2bd03a0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f17b2bd0430>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f17b2c4b3c0>"
|
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": 1676540042526176185,
|
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:": "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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 sha256:4a2d2f05252a164d74a07b31628ee2bfaa71d51e3bc312466bba35fa95dfa685
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:919820e3b9cb70410cf2161b9d948d6370bf1801b6ea921dcfae05b2d5e836df
|
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: 1.21.6
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (207 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 252.87240081490444, "std_reward": 20.629409968737946, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-16T10:03:40.783287"}
|