ghassenhannachi
commited on
Commit
•
6a1696e
1
Parent(s):
d274561
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: 264.37 +/- 13.55
|
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 0x7fb16059d310>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb16059d3a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb16059d430>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb16059d4c0>", "_build": "<function ActorCriticPolicy._build at 0x7fb16059d550>", "forward": "<function ActorCriticPolicy.forward at 0x7fb16059d5e0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fb16059d670>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb16059d700>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb16059d790>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb16059d820>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb16059d8b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb16059d940>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fb16059cb80>"}, "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": 1680349871042597892, "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 sha256:4d80ee9dd0aa1e709d134ecbd2ca9cec2dd0860a726b46ae13a67ba755f1d26e
|
3 |
+
size 147429
|
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 0x7fb16059d310>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb16059d3a0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb16059d430>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb16059d4c0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fb16059d550>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fb16059d5e0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fb16059d670>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb16059d700>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fb16059d790>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb16059d820>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb16059d8b0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb16059d940>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7fb16059cb80>"
|
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": 1680349871042597892,
|
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+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+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:a5cac4a0655040ffda367444b8a96ad2fdd1a1c3d51abfaa3837115a11b2d722
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f9aa3f42d4c3e5266906603d03190eb229905902933a49eaeead194d4e4981e
|
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 (200 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 264.3689171434863, "std_reward": 13.546691387289018, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-01T12:13:48.221345"}
|