magnificent
commited on
Commit
•
4f66828
1
Parent(s):
95c71fb
RL-course unit 1 exercise
Browse files- PPO-rlcourse.zip +3 -0
- PPO-rlcourse/_stable_baselines3_version +1 -0
- PPO-rlcourse/data +94 -0
- PPO-rlcourse/policy.optimizer.pth +3 -0
- PPO-rlcourse/policy.pth +3 -0
- PPO-rlcourse/pytorch_variables.pth +3 -0
- PPO-rlcourse/system_info.txt +7 -0
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
PPO-rlcourse.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bab3f2002427231ed35de832b37817006c1e2b410cf3809961990cf3df6bd4f7
|
3 |
+
size 147198
|
PPO-rlcourse/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.6.2
|
PPO-rlcourse/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 0x7fb3f112af70>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb3f112f040>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb3f112f0d0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb3f112f160>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fb3f112f1f0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fb3f112f280>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb3f112f310>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fb3f112f3a0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb3f112f430>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb3f112f4c0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb3f112f550>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fb3f1129600>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
|
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": 204800,
|
46 |
+
"_total_timesteps": 200000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1671984231736808188,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
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": -0.02400000000000002,
|
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": 200,
|
79 |
+
"n_steps": 512,
|
80 |
+
"gamma": 0.98,
|
81 |
+
"gae_lambda": 0.97,
|
82 |
+
"ent_coef": 0.01,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 128,
|
86 |
+
"n_epochs": 8,
|
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-rlcourse/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4c67b17718204da372619b626abface105a8eb37ae17b0c48de638bad069a8e
|
3 |
+
size 87929
|
PPO-rlcourse/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fed910c60c0fdaf2480ceba43db13fa6b8c006c61e1d649449dac36cb4a7e1d
|
3 |
+
size 43201
|
PPO-rlcourse/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-rlcourse/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
|
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: -84.02 +/- 88.15
|
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 0x7fb3f112af70>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb3f112f040>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb3f112f0d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb3f112f160>", "_build": "<function ActorCriticPolicy._build at 0x7fb3f112f1f0>", "forward": "<function ActorCriticPolicy.forward at 0x7fb3f112f280>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb3f112f310>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb3f112f3a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb3f112f430>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb3f112f4c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb3f112f550>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fb3f1129600>"}, "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": 204800, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1671984231736808188, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAADOu4b19e3A+pj2+vPKiSL5nqMo8BUH2PAAAAAAAAAAA8zO/vdZKkT+Z5jK9cLNovutFiLx2POm8AAAAAAAAAABN+wu9e4aVuklmOjoULTq5PUATOkOXQLkAAIA/AACAP9pjzr4rByE/P1+3uwIRQr2pUp89HpPHvQAAAAAAAAAA/lHhvv2AAzz6Siy+FmJWvllQ8jkaMEQ+AAAAAAAAAADNMzu9wx1Lus7cm7uNqZq2k0o2uyHitjoAAIA/AACAPy3eBD7xMA081gMXvvb76Lwdj5E9GL7ZvQAAgD8AAIA/bXCvvrdRMT6jmZK9H+hXvSgFg7su8Es7AAAAAAAAAAAAWPg9Hx3+uRiSLzuEAGc3zNrJOj5eS7oAAIA/AACAP4NEOj86sLW+ZhyROqzDhbmvrKi+lgfZuQAAgD8AAIA/QIvhvVI4pbktyna6EqkTOeryJzsQFj63AACAPwAAgD86J4G+7haeP8JPJTxzGH++LSADPro++jwAAAAAAAAAAPrlMz4KF127eVgTO3fmJbiZoeW8QRkxugAAgD8AAIA/UIWqPnQQYT+CjtY9CuV5vn4fVT4U60O+AAAAAAAAAABgTLm+x1QKvZLRFjxT1Ai5Ka/HPbCRnDsAAIA/AACAP8b/TD4S9tk8uAyKuxUIAbrjz2k+G7EauwAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_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": -0.02400000000000002, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 200, "n_steps": 512, "gamma": 0.98, "gae_lambda": 0.97, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "n_epochs": 8, "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"}}
|
replay.mp4
ADDED
Binary file (273 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -84.01511342809447, "std_reward": 88.14600701153846, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-25T16:09:22.060594"}
|