Initial commit
Browse files- .gitattributes +2 -0
- README.md +64 -0
- args.yml +65 -0
- ars-MountainCarContinuous-v0.zip +3 -0
- ars-MountainCarContinuous-v0/_stable_baselines3_version +1 -0
- ars-MountainCarContinuous-v0/data +131 -0
- ars-MountainCarContinuous-v0/policy.pth +3 -0
- ars-MountainCarContinuous-v0/pytorch_variables.pth +3 -0
- ars-MountainCarContinuous-v0/system_info.txt +7 -0
- config.yml +21 -0
- env_kwargs.yml +1 -0
- replay.mp4 +3 -0
- results.json +1 -0
- train_eval_metrics.zip +3 -0
- vec_normalize.pkl +3 -0
.gitattributes
CHANGED
@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
29 |
+
vec_normalize.pkl filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- MountainCarContinuous-v0
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: ARS
|
10 |
+
results:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 96.50 +/- 0.78
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: MountainCarContinuous-v0
|
20 |
+
type: MountainCarContinuous-v0
|
21 |
+
---
|
22 |
+
|
23 |
+
# **ARS** Agent playing **MountainCarContinuous-v0**
|
24 |
+
This is a trained model of a **ARS** agent playing **MountainCarContinuous-v0**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
|
26 |
+
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
|
27 |
+
|
28 |
+
The RL Zoo is a training framework for Stable Baselines3
|
29 |
+
reinforcement learning agents,
|
30 |
+
with hyperparameter optimization and pre-trained agents included.
|
31 |
+
|
32 |
+
## Usage (with SB3 RL Zoo)
|
33 |
+
|
34 |
+
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
|
35 |
+
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
|
36 |
+
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
37 |
+
|
38 |
+
```
|
39 |
+
# Download model and save it into the logs/ folder
|
40 |
+
python -m utils.load_from_hub --algo ars --env MountainCarContinuous-v0 -orga sb3 -f logs/
|
41 |
+
python enjoy.py --algo ars --env MountainCarContinuous-v0 -f logs/
|
42 |
+
```
|
43 |
+
|
44 |
+
## Training (with the RL Zoo)
|
45 |
+
```
|
46 |
+
python train.py --algo ars --env MountainCarContinuous-v0 -f logs/
|
47 |
+
# Upload the model and generate video (when possible)
|
48 |
+
python -m utils.push_to_hub --algo ars --env MountainCarContinuous-v0 -f logs/ -orga sb3
|
49 |
+
```
|
50 |
+
|
51 |
+
## Hyperparameters
|
52 |
+
```python
|
53 |
+
OrderedDict([('delta_std', 0.2),
|
54 |
+
('learning_rate', 0.018),
|
55 |
+
('n_delta', 4),
|
56 |
+
('n_envs', 8),
|
57 |
+
('n_timesteps', 500000.0),
|
58 |
+
('n_top', 1),
|
59 |
+
('normalize', 'dict(norm_obs=True, norm_reward=False)'),
|
60 |
+
('policy', 'MlpPolicy'),
|
61 |
+
('policy_kwargs', 'dict(net_arch=[16])'),
|
62 |
+
('zero_policy', False),
|
63 |
+
('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
|
64 |
+
```
|
args.yml
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - algo
|
3 |
+
- ars
|
4 |
+
- - env
|
5 |
+
- MountainCarContinuous-v0
|
6 |
+
- - env_kwargs
|
7 |
+
- null
|
8 |
+
- - eval_episodes
|
9 |
+
- 20
|
10 |
+
- - eval_freq
|
11 |
+
- 100000
|
12 |
+
- - gym_packages
|
13 |
+
- []
|
14 |
+
- - hyperparams
|
15 |
+
- n_envs: 8
|
16 |
+
- - log_folder
|
17 |
+
- rl-trained-agents/
|
18 |
+
- - log_interval
|
19 |
+
- 20
|
20 |
+
- - n_eval_envs
|
21 |
+
- 5
|
22 |
+
- - n_evaluations
|
23 |
+
- 20
|
24 |
+
- - n_jobs
|
25 |
+
- 1
|
26 |
+
- - n_startup_trials
|
27 |
+
- 10
|
28 |
+
- - n_timesteps
|
29 |
+
- -1
|
30 |
+
- - n_trials
|
31 |
+
- 10
|
32 |
+
- - no_optim_plots
|
33 |
+
- false
|
34 |
+
- - num_threads
|
35 |
+
- -1
|
36 |
+
- - optimization_log_path
|
37 |
+
- null
|
38 |
+
- - optimize_hyperparameters
|
39 |
+
- false
|
40 |
+
- - pruner
|
41 |
+
- median
|
42 |
+
- - sampler
|
43 |
+
- tpe
|
44 |
+
- - save_freq
|
45 |
+
- -1
|
46 |
+
- - save_replay_buffer
|
47 |
+
- false
|
48 |
+
- - seed
|
49 |
+
- 2516783745
|
50 |
+
- - storage
|
51 |
+
- null
|
52 |
+
- - study_name
|
53 |
+
- null
|
54 |
+
- - tensorboard_log
|
55 |
+
- ''
|
56 |
+
- - trained_agent
|
57 |
+
- ''
|
58 |
+
- - truncate_last_trajectory
|
59 |
+
- true
|
60 |
+
- - uuid
|
61 |
+
- false
|
62 |
+
- - vec_env
|
63 |
+
- dummy
|
64 |
+
- - verbose
|
65 |
+
- 1
|
ars-MountainCarContinuous-v0.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f52f51c6f7b8379b602b2bacd08bf3a34323c17019ab81a452fbc3520b78d0e4
|
3 |
+
size 15999
|
ars-MountainCarContinuous-v0/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.1a8
|
ars-MountainCarContinuous-v0/data
ADDED
@@ -0,0 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVKgAAAAAAAACMGHNiM19jb250cmliLmFycy5wb2xpY2llc5SMCUFSU1BvbGljeZSTlC4=",
|
5 |
+
"__module__": "sb3_contrib.ars.policies",
|
6 |
+
"__doc__": "\n Policy network for ARS.\n\n :param observation_space: The observation space of the environment\n :param action_space: The action space of the environment\n :param net_arch: Network architecture, defaults to a 2 layers MLP with 64 hidden nodes.\n :param activation_fn: Activation function\n :param squash_output: For continuous actions, whether the output is squashed\n or not using a ``tanh()`` function. If not squashed with tanh the output will instead be clipped.\n ",
|
7 |
+
"__init__": "<function ARSPolicy.__init__ at 0x7f55411cde60>",
|
8 |
+
"_get_constructor_parameters": "<function ARSPolicy._get_constructor_parameters at 0x7f55411d65f0>",
|
9 |
+
"forward": "<function ARSPolicy.forward at 0x7f55411d6680>",
|
10 |
+
"_predict": "<function ARSPolicy._predict at 0x7f55411d6710>",
|
11 |
+
"__abstractmethods__": "frozenset()",
|
12 |
+
"_abc_impl": "<_abc_data object at 0x7f5541498840>"
|
13 |
+
},
|
14 |
+
"verbose": 1,
|
15 |
+
"policy_kwargs": {
|
16 |
+
"net_arch": [
|
17 |
+
16
|
18 |
+
]
|
19 |
+
},
|
20 |
+
"observation_space": {
|
21 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
22 |
+
":serialized:": "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",
|
23 |
+
"dtype": "float32",
|
24 |
+
"low": "[-1.2 -0.07]",
|
25 |
+
"high": "[0.6 0.07]",
|
26 |
+
"bounded_below": "[ True True]",
|
27 |
+
"bounded_above": "[ True True]",
|
28 |
+
"_np_random": null,
|
29 |
+
"_shape": [
|
30 |
+
2
|
31 |
+
]
|
32 |
+
},
|
33 |
+
"action_space": {
|
34 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
35 |
+
":serialized:": "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",
|
36 |
+
"dtype": "float32",
|
37 |
+
"low": "[-1.]",
|
38 |
+
"high": "[1.]",
|
39 |
+
"bounded_below": "[ True]",
|
40 |
+
"bounded_above": "[ True]",
|
41 |
+
"_np_random": "RandomState(MT19937)",
|
42 |
+
"_shape": [
|
43 |
+
1
|
44 |
+
]
|
45 |
+
},
|
46 |
+
"n_envs": 1,
|
47 |
+
"num_timesteps": 501072,
|
48 |
+
"_total_timesteps": 500000,
|
49 |
+
"_num_timesteps_at_start": 0,
|
50 |
+
"seed": 0,
|
51 |
+
"action_noise": null,
|
52 |
+
"start_time": 1642499794.2479646,
|
53 |
+
"learning_rate": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
56 |
+
},
|
57 |
+
"tensorboard_log": null,
|
58 |
+
"lr_schedule": {
|
59 |
+
":type:": "<class 'function'>",
|
60 |
+
":serialized:": "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"
|
61 |
+
},
|
62 |
+
"_last_obs": null,
|
63 |
+
"_last_episode_starts": {
|
64 |
+
":type:": "<class 'numpy.ndarray'>",
|
65 |
+
":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQGUdJRiLg=="
|
66 |
+
},
|
67 |
+
"_last_original_obs": {
|
68 |
+
":type:": "<class 'numpy.ndarray'>",
|
69 |
+
":serialized:": "gASVkgAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLAoaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUMIA4sAvwAAAACUdJRiLg=="
|
70 |
+
},
|
71 |
+
"_episode_num": 0,
|
72 |
+
"use_sde": false,
|
73 |
+
"sde_sample_freq": -1,
|
74 |
+
"_current_progress_remaining": 0.0046399999999999775,
|
75 |
+
"ep_info_buffer": [
|
76 |
+
{
|
77 |
+
"r": 93.068783,
|
78 |
+
"l": 167
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"r": -41.010586,
|
82 |
+
"l": 999
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"r": 94.370722,
|
86 |
+
"l": 156
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"r": 93.211925,
|
90 |
+
"l": 154
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"r": 83.726694,
|
94 |
+
"l": 527
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"r": 94.649334,
|
98 |
+
"l": 233
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"r": 96.341879,
|
102 |
+
"l": 158
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"r": -10.583895,
|
106 |
+
"l": 999
|
107 |
+
}
|
108 |
+
],
|
109 |
+
"ep_success_buffer": {
|
110 |
+
":type:": "<class 'collections.deque'>",
|
111 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
112 |
+
},
|
113 |
+
"_n_updates": 139,
|
114 |
+
"n_delta": 4,
|
115 |
+
"pop_size": 8,
|
116 |
+
"delta_std_schedule": {
|
117 |
+
":type:": "<class 'function'>",
|
118 |
+
":serialized:": "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"
|
119 |
+
},
|
120 |
+
"n_eval_episodes": 1,
|
121 |
+
"n_top": 1,
|
122 |
+
"alive_bonus_offset": 0,
|
123 |
+
"zero_policy": false,
|
124 |
+
"weights": {
|
125 |
+
":type:": "<class 'torch.Tensor'>",
|
126 |
+
":serialized:": "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"
|
127 |
+
},
|
128 |
+
"processes": null,
|
129 |
+
"old_count": 502734.0009,
|
130 |
+
"n_params": 65
|
131 |
+
}
|
ars-MountainCarContinuous-v0/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:881153b5d167503303dabcd0f6b1d606e184d9c1db2367fd298a7aaad2298725
|
3 |
+
size 1951
|
ars-MountainCarContinuous-v0/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
ars-MountainCarContinuous-v0/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.13.0-44-generic-x86_64-with-debian-bullseye-sid #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
|
2 |
+
Python: 3.7.10
|
3 |
+
Stable-Baselines3: 1.5.1a8
|
4 |
+
PyTorch: 1.11.0
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.2
|
7 |
+
Gym: 0.21.0
|
config.yml
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - delta_std
|
3 |
+
- 0.2
|
4 |
+
- - learning_rate
|
5 |
+
- 0.018
|
6 |
+
- - n_delta
|
7 |
+
- 4
|
8 |
+
- - n_envs
|
9 |
+
- 8
|
10 |
+
- - n_timesteps
|
11 |
+
- 500000.0
|
12 |
+
- - n_top
|
13 |
+
- 1
|
14 |
+
- - normalize
|
15 |
+
- dict(norm_obs=True, norm_reward=False)
|
16 |
+
- - policy
|
17 |
+
- MlpPolicy
|
18 |
+
- - policy_kwargs
|
19 |
+
- dict(net_arch=[16])
|
20 |
+
- - zero_policy
|
21 |
+
- false
|
env_kwargs.yml
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d80172333beb4d8a9c543b5e758415cbd1a1311aa44ca98c7e9554cefcb21353
|
3 |
+
size 246680
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 96.5042972, "std_reward": 0.7754145754264337, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T19:26:26.874656"}
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f53c28fd5318afa12515d636238fb66639cf6bb6e8fb24de8f8338cd0f00efe5
|
3 |
+
size 2718
|
vec_normalize.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fb0792148d877091a0ad29aaea91d4a126e5d7df118b50083f44f2b67e234cc
|
3 |
+
size 4266
|