Upload PPO LunarLander-v2 trained agent (RL Huggingface course)
Browse files- LunarLander_v1.zip +3 -0
- LunarLander_v1/_stable_baselines3_version +1 -0
- LunarLander_v1/data +95 -0
- LunarLander_v1/policy.optimizer.pth +3 -0
- LunarLander_v1/policy.pth +3 -0
- LunarLander_v1/pytorch_variables.pth +3 -0
- LunarLander_v1/system_info.txt +7 -0
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
LunarLander_v1.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae5fa96b2ef786d0e701a4b39f4770fd5a4c8e08fa5fdf5f7171d2c6ce3bb5f4
|
3 |
+
size 147424
|
LunarLander_v1/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
LunarLander_v1/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 0x7faec0874f70>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7faec0878040>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7faec08780d0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7faec0878160>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7faec08781f0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7faec0878280>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7faec0878310>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7faec08783a0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7faec0878430>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7faec08784c0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7faec0878550>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7faec08785e0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7faec0872570>"
|
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": 1676321115258692489,
|
52 |
+
"learning_rate": 0.0003,
|
53 |
+
"tensorboard_log": null,
|
54 |
+
"lr_schedule": {
|
55 |
+
":type:": "<class 'function'>",
|
56 |
+
":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
|
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 |
+
}
|
LunarLander_v1/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35b78d7004963f0985dd9bb82a81381b041d2f37261aa6a510fcb2aa32f0d370
|
3 |
+
size 87929
|
LunarLander_v1/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e3e5c555c91ca22c33916aa9bd92128ec393a76e2de200b46c68b3e491e4be5
|
3 |
+
size 43393
|
LunarLander_v1/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
LunarLander_v1/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
|
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: 248.59 +/- 16.04
|
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 0x7faec0874f70>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7faec0878040>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7faec08780d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7faec0878160>", "_build": "<function ActorCriticPolicy._build at 0x7faec08781f0>", "forward": "<function ActorCriticPolicy.forward at 0x7faec0878280>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7faec0878310>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7faec08783a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7faec0878430>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7faec08784c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7faec0878550>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7faec08785e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7faec0872570>"}, "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": 1676321115258692489, "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": "1.21.6", "Gym": "0.21.0"}}
|
replay.mp4
ADDED
Binary file (248 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 248.59476357410531, "std_reward": 16.04064953964665, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-13T21:25:32.781498"}
|