Initial Commit
Browse files- .gitattributes +1 -0
- README.md +62 -0
- args.yml +55 -0
- config.yml +17 -0
- env_kwargs.yml +1 -0
- replay.mp4 +3 -0
- results.json +1 -0
- sac-Pendulum-v1.zip +3 -0
- sac-Pendulum-v1/_stable_baselines3_version +1 -0
- sac-Pendulum-v1/actor.optimizer.pth +3 -0
- sac-Pendulum-v1/critic.optimizer.pth +3 -0
- sac-Pendulum-v1/data +118 -0
- sac-Pendulum-v1/ent_coef_optimizer.pth +3 -0
- sac-Pendulum-v1/policy.pth +3 -0
- sac-Pendulum-v1/pytorch_variables.pth +3 -0
- sac-Pendulum-v1/system_info.txt +7 -0
- train_eval_metrics.zip +3 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ 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
|
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- Pendulum-v1
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: SAC
|
10 |
+
results:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: -183.06 +/- 103.48
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: Pendulum-v1
|
20 |
+
type: Pendulum-v1
|
21 |
+
---
|
22 |
+
|
23 |
+
# **SAC** Agent playing **Pendulum-v1**
|
24 |
+
This is a trained model of a **SAC** agent playing **Pendulum-v1**
|
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 sac --env Pendulum-v1 -orga sb3 -f logs/
|
41 |
+
python enjoy.py --algo sac --env Pendulum-v1 -f logs/
|
42 |
+
```
|
43 |
+
|
44 |
+
## Training (with the RL Zoo)
|
45 |
+
```
|
46 |
+
python train.py --algo sac --env Pendulum-v1 -f logs/
|
47 |
+
# Upload the model and generate video (when possible)
|
48 |
+
python -m utils.push_to_hub --algo sac --env Pendulum-v1 -f logs/ -orga sb3
|
49 |
+
```
|
50 |
+
|
51 |
+
## Hyperparameters
|
52 |
+
```python
|
53 |
+
OrderedDict([('gradient_steps', -1),
|
54 |
+
('learning_rate', 0.001),
|
55 |
+
('n_episodes_rollout', 1),
|
56 |
+
('n_timesteps', 20000),
|
57 |
+
('policy', 'MlpPolicy'),
|
58 |
+
('policy_kwargs', 'dict(log_std_init=-2, net_arch=[64, 64])'),
|
59 |
+
('train_freq', -1),
|
60 |
+
('use_sde', True),
|
61 |
+
('normalize', False)])
|
62 |
+
```
|
args.yml
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - algo
|
3 |
+
- sac
|
4 |
+
- - env
|
5 |
+
- Pendulum-v0
|
6 |
+
- - env_kwargs
|
7 |
+
- null
|
8 |
+
- - eval_episodes
|
9 |
+
- 5
|
10 |
+
- - eval_freq
|
11 |
+
- 10000
|
12 |
+
- - gym_packages
|
13 |
+
- []
|
14 |
+
- - hyperparams
|
15 |
+
- null
|
16 |
+
- - log_folder
|
17 |
+
- rl-trained-agents/
|
18 |
+
- - log_interval
|
19 |
+
- -1
|
20 |
+
- - n_evaluations
|
21 |
+
- 20
|
22 |
+
- - n_jobs
|
23 |
+
- 1
|
24 |
+
- - n_startup_trials
|
25 |
+
- 10
|
26 |
+
- - n_timesteps
|
27 |
+
- -1
|
28 |
+
- - n_trials
|
29 |
+
- 10
|
30 |
+
- - num_threads
|
31 |
+
- 2
|
32 |
+
- - optimize_hyperparameters
|
33 |
+
- false
|
34 |
+
- - pruner
|
35 |
+
- median
|
36 |
+
- - sampler
|
37 |
+
- tpe
|
38 |
+
- - save_freq
|
39 |
+
- -1
|
40 |
+
- - save_replay_buffer
|
41 |
+
- false
|
42 |
+
- - seed
|
43 |
+
- 1228490524
|
44 |
+
- - storage
|
45 |
+
- null
|
46 |
+
- - study_name
|
47 |
+
- null
|
48 |
+
- - tensorboard_log
|
49 |
+
- ''
|
50 |
+
- - trained_agent
|
51 |
+
- ''
|
52 |
+
- - uuid
|
53 |
+
- false
|
54 |
+
- - verbose
|
55 |
+
- 1
|
config.yml
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - gradient_steps
|
3 |
+
- -1
|
4 |
+
- - learning_rate
|
5 |
+
- 0.001
|
6 |
+
- - n_episodes_rollout
|
7 |
+
- 1
|
8 |
+
- - n_timesteps
|
9 |
+
- 20000
|
10 |
+
- - policy
|
11 |
+
- MlpPolicy
|
12 |
+
- - policy_kwargs
|
13 |
+
- dict(log_std_init=-2, net_arch=[64, 64])
|
14 |
+
- - train_freq
|
15 |
+
- -1
|
16 |
+
- - use_sde
|
17 |
+
- true
|
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:d1175d6d23707ecec29c40531ff02306ddf54c6ad13dc39569396db0602d001b
|
3 |
+
size 163499
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -183.05522760000002, "std_reward": 103.48458808056235, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-22T21:55:31.844628"}
|
sac-Pendulum-v1.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dbc7ac7053c8c7174881d3209a02134ea3f1670f77510e8bb24b85439fe8b00
|
3 |
+
size 245829
|
sac-Pendulum-v1/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.1a6
|
sac-Pendulum-v1/actor.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92eff6d1b7e877d1fd7c9a1c23eba6fbcb3ed510f28c56f06a372f41f270afff
|
3 |
+
size 40059
|
sac-Pendulum-v1/critic.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68e34a81bc1ffe8c1a85907f516a68997597fc273a2834030b5c3761f5f46a2b
|
3 |
+
size 78877
|
sac-Pendulum-v1/data
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=",
|
5 |
+
"__module__": "stable_baselines3.sac.policies",
|
6 |
+
"__doc__": "\n Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\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()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\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 :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ",
|
7 |
+
"__init__": "<function SACPolicy.__init__ at 0x7f1c154d9b00>",
|
8 |
+
"_build": "<function SACPolicy._build at 0x7f1c154d9b90>",
|
9 |
+
"_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f1c154d9c20>",
|
10 |
+
"reset_noise": "<function SACPolicy.reset_noise at 0x7f1c154d9cb0>",
|
11 |
+
"make_actor": "<function SACPolicy.make_actor at 0x7f1c154d9d40>",
|
12 |
+
"make_critic": "<function SACPolicy.make_critic at 0x7f1c154d9dd0>",
|
13 |
+
"forward": "<function SACPolicy.forward at 0x7f1c154d9e60>",
|
14 |
+
"_predict": "<function SACPolicy._predict at 0x7f1c154d9ef0>",
|
15 |
+
"set_training_mode": "<function SACPolicy.set_training_mode at 0x7f1c154d9f80>",
|
16 |
+
"__abstractmethods__": "frozenset()",
|
17 |
+
"_abc_impl": "<_abc_data object at 0x7f1c154c58d0>"
|
18 |
+
},
|
19 |
+
"verbose": 1,
|
20 |
+
"policy_kwargs": {
|
21 |
+
"log_std_init": -2,
|
22 |
+
"net_arch": [
|
23 |
+
64,
|
24 |
+
64
|
25 |
+
],
|
26 |
+
"use_sde": true
|
27 |
+
},
|
28 |
+
"observation_space": {
|
29 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
30 |
+
":serialized:": "gAWV9QsAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMA2xvd5SMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAAAAAgL8AAIC/AAAAwZRoCksDhZSMAUOUdJRSlIwEaGlnaJRoECiWDAAAAAAAAAAAAIA/AACAPwAAAEGUaApLA4WUaBN0lFKUjA1ib3VuZGVkX2JlbG93lGgQKJYDAAAAAAAAAAEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksDhZRoE3SUUpSMDWJvdW5kZWRfYWJvdmWUaBAolgMAAAAAAAAAAQEBlGgfSwOFlGgTdJRSlIwGX3NoYXBllEsDhZSMCl9ucF9yYW5kb22UjBRudW1weS5yYW5kb20uX3BpY2tsZZSMEl9fcmFuZG9tc3RhdGVfY3RvcpSTlIwHTVQxOTkzN5SFlFKUfZQojA1iaXRfZ2VuZXJhdG9ylGgwjAVzdGF0ZZR9lCiMA2tleZRoECiWwAkAAAAAAAAAAACAkZjUxvkmFlGRFZt/lNEXiDqB8fbl61sOdWhaV0XABcnQyvfNbnqureWOYi5Rxa3DIcjYA8fS72oMAxYZp9vvqDFAScGI038YNvH0ATdbYzO4jnpyKhPCFSxHK+790W4VK4RTTqQq8Rs3hweZzfyTkIXquZgZ8/JZcyNeFcKphw6lQ+zK9iy1S7LMKimQRd5MbirH5bOdcvw9bZmW7v+4tnhNR+9wQ3WQthE8zqsrxNG93OD+Z5H70k6QxksLbsnjOUsR6P0A5edADMUAaqGkQJtGv74oJEeMdX/og7gDk9D3Wip2Tv5CYiGx0UtyTGGVS5RG8oDLDEFpx2t094ePzZjvfyUXwGXbe8i3rJfB2QoQPR3u5nNHdexw4sPZs5ZTTmgal/ccAFf3NgnACTwAaYDM/+YUe8J3tNgvREV4EUHlFKXonOvWVAWPGhBoQ4KAcAoVeS5thynMibQAM8qNmxYmCOmdN/1lvcG7UF6WxXtxqwmp2NXAgNJcdj8lShC+6f1OzvKBNlsDRwCW8pIog79heZgstJLa9MBSyTWc/sHm2R3Ma2+37J18vsR/fe5rAKqvOtOY4d95QNBopLQJqrWIW0NTo94tzw9cTmWyLldDvrC0pWkHuixqEYGsLZZgSEhJHhkbWi/wNDVC6qeKuf8ARB1oc29+4O4UQUkMM79YU/YQXLW7ov+vxhtFkQX4vN/5OT4j/FpBcsWFxMdo3eiFqSYQAZ2caY1dept5JC8DU7Zbnu1ZXR0WXU9OQjylGX0vG1qYJLiaaAf+fOaCjfn6Vp9dgLKTDHfTLWo5aPa/4Ki7g/us2SmHgy0aNHVpWvdSxbdtFzpS32nrCnMvNKDc+URzoWsy03PpFVesZc4zZdSR5dfwlO2M55t3YDCfTq6NH7KgzSeVruS/50xUOqzevfk7G69CNeeD3DsdW8YqQEi//XS0vatw5qLejJ+1DTNOdNXAiEtWZiuMLjFDYc9uUcS6BXobAesYbYitB7H/dqHhAZJdYIHAdeGlk3iWB99H0UmHnkXXV1fa6c99iklfTNtrBbvGmbluHIhSU9ZX6yOyBdq4Kz9oJcacg25c0CovqHQKOAdsi6d9tL3PRtDZpcs/DADUO7PJT4p0XBhVwPpEv4kpYx7TTk27zHkDF55rHHmkCzz69Pm7FArYtOg3ftW1dnGtKMY4pK3k8syJ1gWVdEdnKKg5N3aY6pUdDLfKsfpgSR08sme70uxc0+OqFZusqkAO62588ytvBTZqIM9fBNdnxJlH1X0DzwXeJZ+Md2P1u9LUYDdzfiEKMvm5MEov2wGnFczcorvNnRa92dSz/pXkCWpivElp/Rj9yU5Zlpk1XBShy4O5KoubTp8Jrynm/X2LoI4ABi0KgQCC2z5oEW+eRM6OGHBDyYGEKUPFj1XqJohya8j05KD4BPRWi6foGZ4Hm5aoqLMhktSu9EFA+puTdZVwxhf4Y4VYyt3o82Yy6s3INbmQHbRQV0KO7sxoyoBfTawPn5mDvHjnc11IXSCak8Drqcnvj1mC/JJyKJCdAau0AyjMAFw3f5hJ8mz5torTM3eq7O1XQDqeM8tv5vNc0bZ9qvdyo+SyJYxRWXf6CeC7Q/CJ38chYYHovxFn93R3ujDWG1V2I3cLJf6/yS1g5JwgtH7qY8QDs57T2X/MKufFrA+CcD8h4p5wZQvCpFe+0+0tNM16FtmdPVwxzW836BTs7Fl6U80LYeGE8o7FY223DC+t/zES5ZyZWSuLpz/vRB6DuwgSQ3tK72I4y2WFm9XPUvVIPUK8qAozVDrNao8+awOK6dKwj8cIIZUE4B/4bspfafPioiSQqQEenpAbtPKpDD2hjw1LaVPzw6CW1h3oLPSyf9HqAY4w2TpXvCdgO69BJtopMQEHvt6eUf7SfnEQ8RuuQuSr/zbZrzmmWRP+6uS6NDKrfZGr5bUbEV/iFOZSy046Rume9NzqnqoOPuCOd4GHa3fkF6R/hpFfJLLzYfaxvUwXdPuKCI/ISRV+fOpMqqgpci5OIiZdaO1HDjrAW++DByBVtpLmb2nMYJWCm6VP0gxfeRcTowI9yY3vPOW5fqCezRE7QtMmudS896/K2DfDmYuN3EUPlrC/AYmVgPGLilgjz71zLAqIXJWcMvvf+qVP2w5/5kVh/Fw3Z39kYVq8TD7H1heiafLv1aOzEULfWDzLQzD4c0MMc/YUuh8zuue6SWevpJZiCzSiBCnfXrMK2T8oDhbtW2AgNopLak6rkMIE8ac3i6kiskqjdAFukDi87/6e3O3Aop+MaeIggbQpZaMJSrC9kcUn9KaPza8ItFHgAjuwG5Q2/M9DjVXy/jx+LD4cRy4VDw8nN4SUxMSeaL2T4hPp/NVoIrohUDgKbHYRS05dlmRFDZ/xFmM2GtKh6dt7N/cxo7Pr/63U2gQ2H0CCNQPwQAiVUz3T6sL2MVv0MOEIfDacro1F0MVqypoN01SZ3gXSSCeda0nY4z1ZTlh/T0vuFifjJB8HgffuKmJ4fDArhxg4Aw+7wZRnNPfC2L6IFUN7lAzUTeykdzA8h6CL3XvpdhYYGiyz6S2uafFy/S3xUQ/X5pNWysRZ+8ecIoMZwAEFxJ5swVBljwJIaNLUBSzLaBpCnhx3S5TDD4X3j1ZosKDuf+bpcIMigAumR1oMKECJtM/I5n7jNd8TGvPtigljdCj/MMP0KkMLBAZnyCZ488kIUFV8xH4+fnZEqVJ4NpIeYK+g56qx6WVE0qgule7unIcX5fyNesv0bjK/bLZjOVbXXaa2/PYqB9b+y0O6ABAu1HHWHMNtoNfeeAmwEC2vPMt/uZkvOMlveYy9zf2dXTiZtjiSpzZ8bg7Mh5VL8VSubDezyTWydGUElPOPfTQ84GKGRYWIkRjYOzmhyfyYMLITiq75ZHhQQEVD2SSjlqoEyIurOcqospLqHy8nTkkYnj8U9IhREjeJIX5rDVHs2XBW3PVHzE2bsyEtlaUfK2wJ3XjQGyv3ITBvTU2iI0WWNrJUxrOEfGiqL6JAt6SuxIELEtXdIXq2d45di5QjjIqJhwHfkA71qRTRa47xMmnOy0/lnadSRompN6jWqAdgTs9LjvkeQPSx69RDXYQtZJfNNX4uX315EhG/8QGcbmRg3PadfgSCCib8YjzrYqxAFCNve/49GhdqW7FcKXxaVB310ydlcmNBTKckgPAMFShbeeOEP25pMSws7xuMIFEgur4WDtd4fITsVRsYwPxywoWd8bczCIu/4dYW9T6KxDeCjTsDrwVWaEIxr92ujchxMrp6Hp7PV2OyqBOveL+T5DZJUxnvX169VneUaAeMAnU0lImIh5RSlChLA2gLTk5OSv////9K/////0sAdJRiTXAChZRoE3SUUpSMA3Bvc5RNcAJ1jAloYXNfZ2F1c3OUSwCMBWdhdXNzlEcAAAAAAAAAAHVidWIu",
|
31 |
+
"dtype": "float32",
|
32 |
+
"low": "[-1. -1. -8.]",
|
33 |
+
"high": "[1. 1. 8.]",
|
34 |
+
"bounded_below": "[ True True True]",
|
35 |
+
"bounded_above": "[ True True True]",
|
36 |
+
"_shape": [
|
37 |
+
3
|
38 |
+
],
|
39 |
+
"_np_random": "RandomState(MT19937)"
|
40 |
+
},
|
41 |
+
"action_space": {
|
42 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
43 |
+
":serialized:": "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",
|
44 |
+
"dtype": "float32",
|
45 |
+
"low": "[-2.]",
|
46 |
+
"high": "[2.]",
|
47 |
+
"bounded_below": "[ True]",
|
48 |
+
"bounded_above": "[ True]",
|
49 |
+
"_shape": [
|
50 |
+
1
|
51 |
+
],
|
52 |
+
"_np_random": "RandomState(MT19937)"
|
53 |
+
},
|
54 |
+
"n_envs": 1,
|
55 |
+
"num_timesteps": 20000,
|
56 |
+
"_total_timesteps": 20000,
|
57 |
+
"_num_timesteps_at_start": 0,
|
58 |
+
"seed": 0,
|
59 |
+
"action_noise": null,
|
60 |
+
"start_time": 1594906729.0364032,
|
61 |
+
"learning_rate": {
|
62 |
+
":type:": "<class 'function'>",
|
63 |
+
":serialized:": "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"
|
64 |
+
},
|
65 |
+
"tensorboard_log": null,
|
66 |
+
"lr_schedule": {
|
67 |
+
":type:": "<class 'function'>",
|
68 |
+
":serialized:": "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"
|
69 |
+
},
|
70 |
+
"_last_obs": null,
|
71 |
+
"_last_episode_starts": null,
|
72 |
+
"_last_original_obs": {
|
73 |
+
":type:": "<class 'numpy.ndarray'>",
|
74 |
+
":serialized:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAAOLvfD/u7R0+uYSgtZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlC4="
|
75 |
+
},
|
76 |
+
"_episode_num": 100,
|
77 |
+
"use_sde": true,
|
78 |
+
"sde_sample_freq": -1,
|
79 |
+
"_current_progress_remaining": 0.0,
|
80 |
+
"ep_info_buffer": {
|
81 |
+
":type:": "<class 'collections.deque'>",
|
82 |
+
":serialized:": "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"
|
83 |
+
},
|
84 |
+
"ep_success_buffer": {
|
85 |
+
":type:": "<class 'collections.deque'>",
|
86 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
87 |
+
},
|
88 |
+
"_n_updates": 20000,
|
89 |
+
"buffer_size": 1,
|
90 |
+
"batch_size": 256,
|
91 |
+
"learning_starts": 100,
|
92 |
+
"tau": 0.005,
|
93 |
+
"gamma": 0.99,
|
94 |
+
"gradient_steps": -1,
|
95 |
+
"optimize_memory_usage": false,
|
96 |
+
"replay_buffer_class": {
|
97 |
+
":type:": "<class 'abc.ABCMeta'>",
|
98 |
+
":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
99 |
+
"__module__": "stable_baselines3.common.buffers",
|
100 |
+
"__doc__": "\n Replay buffer used in off-policy algorithms like SAC/TD3.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device:\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n of the replay buffer which reduces by almost a factor two the memory used,\n at a cost of more complexity.\n See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ",
|
101 |
+
"__init__": "<function ReplayBuffer.__init__ at 0x7f1c1593ecb0>",
|
102 |
+
"add": "<function ReplayBuffer.add at 0x7f1c1593ed40>",
|
103 |
+
"sample": "<function ReplayBuffer.sample at 0x7f1c15933440>",
|
104 |
+
"_get_samples": "<function ReplayBuffer._get_samples at 0x7f1c159334d0>",
|
105 |
+
"__abstractmethods__": "frozenset()",
|
106 |
+
"_abc_impl": "<_abc_data object at 0x7f1c1599e3f0>"
|
107 |
+
},
|
108 |
+
"replay_buffer_kwargs": {},
|
109 |
+
"train_freq": {
|
110 |
+
":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
|
111 |
+
":serialized:": "gAWVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RK/////2gAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
|
112 |
+
},
|
113 |
+
"use_sde_at_warmup": false,
|
114 |
+
"target_entropy": -1.0,
|
115 |
+
"ent_coef": "auto",
|
116 |
+
"target_update_interval": 1,
|
117 |
+
"n_episodes_rollout": 1
|
118 |
+
}
|
sac-Pendulum-v1/ent_coef_optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90fe68288e56808ca47de578855ddde74448da3071221e41a7d5beb541e251cb
|
3 |
+
size 1191
|
sac-Pendulum-v1/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6df1e5064252049d0c2b85379017680caec419fe5876e3bdbe8970c390dd4fbd
|
3 |
+
size 101000
|
sac-Pendulum-v1/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b49e3e131f68a2c82af7f4a7a03d153b4f2b49d8720cc268f854efe85711e196
|
3 |
+
size 747
|
sac-Pendulum-v1/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.4.0-110-generic-x86_64-with-debian-bullseye-sid #124-Ubuntu SMP Thu Apr 14 19:46:19 UTC 2022
|
2 |
+
Python: 3.7.12
|
3 |
+
Stable-Baselines3: 1.5.1a6
|
4 |
+
PyTorch: 1.11.0+cpu
|
5 |
+
GPU Enabled: False
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c10d45aaabe0dfb521d8128b6d98b9b25b7615cbc8912a9cdd4016b4efc5a8b
|
3 |
+
size 3904
|