croumegous
commited on
Commit
•
239bfed
1
Parent(s):
91a6e73
Upload first PPO LunarLander-v2 trained agent
Browse files- README.md +36 -0
- config.json +1 -0
- first-model-ppo-LunarLander-v2.zip +3 -0
- first-model-ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- first-model-ppo-LunarLander-v2/data +94 -0
- first-model-ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- first-model-ppo-LunarLander-v2/policy.pth +3 -0
- first-model-ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- first-model-ppo-LunarLander-v2/system_info.txt +7 -0
- replay.mp4 +0 -0
- results.json +1 -0
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 287.39 +/- 16.63
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: LunarLander-v2
|
20 |
+
type: LunarLander-v2
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **LunarLander-v2**
|
24 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
26 |
+
|
27 |
+
## Usage (with Stable-baselines3)
|
28 |
+
TODO: Add your code
|
29 |
+
|
30 |
+
|
31 |
+
```python
|
32 |
+
from stable_baselines3 import ...
|
33 |
+
from huggingface_sb3 import load_from_hub
|
34 |
+
|
35 |
+
...
|
36 |
+
```
|
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 0x7fb94655e310>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb94655e3a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb94655e430>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb94655e4c0>", "_build": "<function ActorCriticPolicy._build at 0x7fb94655e550>", "forward": "<function ActorCriticPolicy.forward at 0x7fb94655e5e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb94655e670>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb94655e700>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb94655e790>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb94655e820>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb94655e8b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fb94655f800>"}, "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": 8, "num_timesteps": 1507328, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1657386771.4378717, "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:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 736, "n_steps": 2048, "gamma": 0.999, "gae_lambda": 0.98, "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-5.4.0-121-generic-x86_64-with-glibc2.31 #137-Ubuntu SMP Wed Jun 15 13:33:07 UTC 2022", "Python": "3.9.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "False", "Numpy": "1.21.5", "Gym": "0.21.0"}}
|
first-model-ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83a0fe2dbcc5c089251c88fe9be98b9dab6f8d08d10e150b35a348be23a35975
|
3 |
+
size 143356
|
first-model-ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
first-model-ppo-LunarLander-v2/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 0x7fb94655e310>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb94655e3a0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb94655e430>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb94655e4c0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fb94655e550>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fb94655e5e0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb94655e670>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fb94655e700>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb94655e790>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb94655e820>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb94655e8b0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc._abc_data object at 0x7fb94655f800>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
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": 8,
|
45 |
+
"num_timesteps": 1507328,
|
46 |
+
"_total_timesteps": 1500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1657386771.4378717,
|
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:": "gAWVdQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAQAAAAAAAM0iZb0quik+Gv8BPq8Vr74lZH89f6SsugAAAAAAAAAAemoyPsREgT6Qj6e+Wv/DvuCWjr0xkBe9AAAAAAAAAADmey2+mpm2P6ZlDb9heaa+70yVvkZo8r4AAAAAAAAAAJrpbDwAArg++E32Pd1avb4ViKM9VNQLPQAAAAAAAAAAc/1tPiWITz+z8Mm8IoQFvzFVnz444hG+AAAAAAAAAACmIFu+PPbvPgdzTD5C7rO+Vcgfvs6UmD0AAAAAAAAAALOmjj5yLEI/FtxUPtBx8r6wHuU+uTIWPQAAAAAAAAAAgH9FPb66nD/RyR4+3b0MvwCBOj0No7A9AAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwhLCIaUjAFDlHSUUpQu"
|
60 |
+
},
|
61 |
+
"_last_episode_starts": {
|
62 |
+
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlC4="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.004885333333333408,
|
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": 736,
|
79 |
+
"n_steps": 2048,
|
80 |
+
"gamma": 0.999,
|
81 |
+
"gae_lambda": 0.98,
|
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 |
+
}
|
first-model-ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7e808b204cc05ee1db4ff7f730750d711ec60677f92839847da8052b31cf013
|
3 |
+
size 84637
|
first-model-ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e9e14f46aed97ff3cdacb6a0c6ef4bb76e4a7d12f3a8366ca4b865128bd2a67
|
3 |
+
size 43073
|
first-model-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
|
first-model-ppo-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.4.0-121-generic-x86_64-with-glibc2.31 #137-Ubuntu SMP Wed Jun 15 13:33:07 UTC 2022
|
2 |
+
Python: 3.9.12
|
3 |
+
Stable-Baselines3: 1.5.0
|
4 |
+
PyTorch: 1.11.0+cu102
|
5 |
+
GPU Enabled: False
|
6 |
+
Numpy: 1.21.5
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (197 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 287.3922199107994, "std_reward": 16.62674079444803, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-09T19:34:52.322137"}
|