first commit for hf rl course unit1
Browse files- README.md +37 -0
- config.json +1 -0
- hf_lander_ab_v1.zip +3 -0
- hf_lander_ab_v1/_stable_baselines3_version +1 -0
- hf_lander_ab_v1/data +96 -0
- hf_lander_ab_v1/policy.optimizer.pth +3 -0
- hf_lander_ab_v1/policy.pth +3 -0
- hf_lander_ab_v1/pytorch_variables.pth +3 -0
- hf_lander_ab_v1/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: 262.93 +/- 16.07
|
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 0x7f94777ed820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f94777ed8b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f94777ed940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f94777ed9d0>", "_build": "<function ActorCriticPolicy._build at 0x7f94777eda60>", "forward": "<function ActorCriticPolicy.forward at 0x7f94777edaf0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f94777edb80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f94777edc10>", "_predict": "<function ActorCriticPolicy._predict at 0x7f94777edca0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f94777edd30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f94777eddc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f94777ede50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f9477808dc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1681634119243931437, "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, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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, "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": "1.8.0", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
hf_lander_ab_v1.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a96aed756d8db64cba1488d4acdceda82316c6fdd9ba7647ffe3ee375d8c9126
|
3 |
+
size 147395
|
hf_lander_ab_v1/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.8.0
|
hf_lander_ab_v1/data
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7f94777ed820>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f94777ed8b0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f94777ed940>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f94777ed9d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f94777eda60>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f94777edaf0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f94777edb80>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f94777edc10>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f94777edca0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f94777edd30>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f94777eddc0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f94777ede50>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f9477808dc0>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 1015808,
|
25 |
+
"_total_timesteps": 1000000,
|
26 |
+
"_num_timesteps_at_start": 0,
|
27 |
+
"seed": null,
|
28 |
+
"action_noise": null,
|
29 |
+
"start_time": 1681634119243931437,
|
30 |
+
"learning_rate": 0.0003,
|
31 |
+
"tensorboard_log": null,
|
32 |
+
"lr_schedule": {
|
33 |
+
":type:": "<class 'function'>",
|
34 |
+
":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
|
35 |
+
},
|
36 |
+
"_last_obs": {
|
37 |
+
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "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"
|
39 |
+
},
|
40 |
+
"_last_episode_starts": {
|
41 |
+
":type:": "<class 'numpy.ndarray'>",
|
42 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
43 |
+
},
|
44 |
+
"_last_original_obs": null,
|
45 |
+
"_episode_num": 0,
|
46 |
+
"use_sde": false,
|
47 |
+
"sde_sample_freq": -1,
|
48 |
+
"_current_progress_remaining": -0.015808000000000044,
|
49 |
+
"_stats_window_size": 100,
|
50 |
+
"ep_info_buffer": {
|
51 |
+
":type:": "<class 'collections.deque'>",
|
52 |
+
":serialized:": "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"
|
53 |
+
},
|
54 |
+
"ep_success_buffer": {
|
55 |
+
":type:": "<class 'collections.deque'>",
|
56 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
57 |
+
},
|
58 |
+
"_n_updates": 248,
|
59 |
+
"observation_space": {
|
60 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
61 |
+
":serialized:": "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",
|
62 |
+
"dtype": "float32",
|
63 |
+
"_shape": [
|
64 |
+
8
|
65 |
+
],
|
66 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
67 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
68 |
+
"bounded_below": "[False False False False False False False False]",
|
69 |
+
"bounded_above": "[False False False False False False False False]",
|
70 |
+
"_np_random": null
|
71 |
+
},
|
72 |
+
"action_space": {
|
73 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
74 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
75 |
+
"n": 4,
|
76 |
+
"_shape": [],
|
77 |
+
"dtype": "int64",
|
78 |
+
"_np_random": null
|
79 |
+
},
|
80 |
+
"n_envs": 16,
|
81 |
+
"n_steps": 1024,
|
82 |
+
"gamma": 0.999,
|
83 |
+
"gae_lambda": 0.98,
|
84 |
+
"ent_coef": 0.01,
|
85 |
+
"vf_coef": 0.5,
|
86 |
+
"max_grad_norm": 0.5,
|
87 |
+
"batch_size": 64,
|
88 |
+
"n_epochs": 4,
|
89 |
+
"clip_range": {
|
90 |
+
":type:": "<class 'function'>",
|
91 |
+
":serialized:": "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"
|
92 |
+
},
|
93 |
+
"clip_range_vf": null,
|
94 |
+
"normalize_advantage": true,
|
95 |
+
"target_kl": null
|
96 |
+
}
|
hf_lander_ab_v1/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e0f8ee98e861262111a2a3d4e1d84c33d419ff7c74b0fbcd35fe8d4bc3c4454
|
3 |
+
size 87929
|
hf_lander_ab_v1/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0308a6441e0bdd825b491dfbe1730eaea8d36f028f310c23bab763cb440796c8
|
3 |
+
size 43329
|
hf_lander_ab_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
|
hf_lander_ab_v1/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: 1.8.0
|
4 |
+
- PyTorch: 2.0.0+cu118
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (228 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 262.92560840757375, "std_reward": 16.073674224307336, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-16T09:02:51.551849"}
|