Initial commit
Browse files- .gitattributes +2 -0
- README.md +59 -0
- args.yml +65 -0
- config.yml +11 -0
- env_kwargs.yml +1 -0
- replay.mp4 +3 -0
- results.json +1 -0
- train_eval_metrics.zip +3 -0
- trpo-Acrobot-v1.zip +3 -0
- trpo-Acrobot-v1/_stable_baselines3_version +1 -0
- trpo-Acrobot-v1/data +94 -0
- trpo-Acrobot-v1/policy.optimizer.pth +3 -0
- trpo-Acrobot-v1/policy.pth +3 -0
- trpo-Acrobot-v1/pytorch_variables.pth +3 -0
- trpo-Acrobot-v1/system_info.txt +7 -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 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- Acrobot-v1
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: TRPO
|
10 |
+
results:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: -87.40 +/- 12.60
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: Acrobot-v1
|
20 |
+
type: Acrobot-v1
|
21 |
+
---
|
22 |
+
|
23 |
+
# **TRPO** Agent playing **Acrobot-v1**
|
24 |
+
This is a trained model of a **TRPO** agent playing **Acrobot-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 trpo --env Acrobot-v1 -orga sb3 -f logs/
|
41 |
+
python enjoy.py --algo trpo --env Acrobot-v1 -f logs/
|
42 |
+
```
|
43 |
+
|
44 |
+
## Training (with the RL Zoo)
|
45 |
+
```
|
46 |
+
python train.py --algo trpo --env Acrobot-v1 -f logs/
|
47 |
+
# Upload the model and generate video (when possible)
|
48 |
+
python -m utils.push_to_hub --algo trpo --env Acrobot-v1 -f logs/ -orga sb3
|
49 |
+
```
|
50 |
+
|
51 |
+
## Hyperparameters
|
52 |
+
```python
|
53 |
+
OrderedDict([('n_envs', 2),
|
54 |
+
('n_steps', 1024),
|
55 |
+
('n_timesteps', 100000.0),
|
56 |
+
('normalize', True),
|
57 |
+
('policy', 'MlpPolicy'),
|
58 |
+
('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
|
59 |
+
```
|
args.yml
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - algo
|
3 |
+
- trpo
|
4 |
+
- - env
|
5 |
+
- Acrobot-v1
|
6 |
+
- - env_kwargs
|
7 |
+
- null
|
8 |
+
- - eval_episodes
|
9 |
+
- 20
|
10 |
+
- - eval_freq
|
11 |
+
- 10000
|
12 |
+
- - gym_packages
|
13 |
+
- []
|
14 |
+
- - hyperparams
|
15 |
+
- null
|
16 |
+
- - log_folder
|
17 |
+
- logs
|
18 |
+
- - log_interval
|
19 |
+
- -1
|
20 |
+
- - n_eval_envs
|
21 |
+
- 10
|
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 |
+
- 1786045309
|
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
|
config.yml
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - n_envs
|
3 |
+
- 2
|
4 |
+
- - n_steps
|
5 |
+
- 1024
|
6 |
+
- - n_timesteps
|
7 |
+
- 100000.0
|
8 |
+
- - normalize
|
9 |
+
- true
|
10 |
+
- - policy
|
11 |
+
- MlpPolicy
|
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 sha256:1b8206e2abdef479f8654552941b68351c704fd2b5e27dddc0ad34d29e295e66
|
3 |
+
size 972617
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -87.4, "std_reward": 12.603174203350518, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T12:57:02.890071"}
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bce86c35d5ad5d55d3226ff44a9bb2be9f8b9b5c72b0171e1c34cc0816cada2
|
3 |
+
size 23768
|
trpo-Acrobot-v1.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9221c2f9d309ecf179b6cbcb522b23b4ead54fe996df9c9bf549885903ecaac9
|
3 |
+
size 99415
|
trpo-Acrobot-v1/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.1a8
|
trpo-Acrobot-v1/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 0x7f35c1f2c950>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f35c1f2c9e0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f35c1f2ca70>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f35c1f2cb00>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f35c1f2cb90>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f35c1f2cc20>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f35c1f2ccb0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f35c1f2cd40>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f35c1f2cdd0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f35c1f2ce60>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f35c1f2cef0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f35c1f7d840>"
|
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 |
+
"low": "[ -1. -1. -1. -1. -12.566371 -28.274334]",
|
28 |
+
"high": "[ 1. 1. 1. 1. 12.566371 28.274334]",
|
29 |
+
"bounded_below": "[ True True True True True True]",
|
30 |
+
"bounded_above": "[ True True True True True True]",
|
31 |
+
"_np_random": null,
|
32 |
+
"_shape": [
|
33 |
+
6
|
34 |
+
]
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "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",
|
39 |
+
"n": 3,
|
40 |
+
"dtype": "int64",
|
41 |
+
"_np_random": "RandomState(MT19937)",
|
42 |
+
"_shape": []
|
43 |
+
},
|
44 |
+
"n_envs": 2,
|
45 |
+
"num_timesteps": 100352,
|
46 |
+
"_total_timesteps": 100000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": 0,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1640769474.6221268,
|
51 |
+
"learning_rate": 0.001,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
56 |
+
},
|
57 |
+
"_last_obs": null,
|
58 |
+
"_last_episode_starts": {
|
59 |
+
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "gASVigAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwKFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAgAAlHSUYi4="
|
61 |
+
},
|
62 |
+
"_last_original_obs": {
|
63 |
+
":type:": "<class 'numpy.ndarray'>",
|
64 |
+
":serialized:": "gASVugAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwJLBoaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUMw/2x/P78Yib3b0X8/tq4ZvVvttj0bzGq9lPJ/P6jIpbwaZX8/gLmMPf95WT3Wkn49lHSUYi4="
|
65 |
+
},
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.0035199999999999676,
|
70 |
+
"ep_info_buffer": {
|
71 |
+
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "gASV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwF0AAAAAAACMAWyUS3WMAXSUR0BeJyKWLP2PdX2UKGgGR8BPAAAAAAAAaAdLP2gIR0BeKcriEQGwdX2UKGgGR8BTwAAAAAAAaAdLUGgIR0BeMZjUd7v5dX2UKGgGR8BVQAAAAAAAaAdLVmgIR0BeNOS8rZrYdX2UKGgGR8BSgAAAAAAAaAdLS2gIR0BeXAOz6ab4dX2UKGgGR8BRAAAAAAAAaAdLRWgIR0BeXn7xd6cBdX2UKGgGR8BUwAAAAAAAaAdLVGgIR0BeZsoMKCxvdX2UKGgGR8BXAAAAAAAAaAdLXWgIR0Bea1CkXUH6dX2UKGgGR8BagAAAAAAAaAdLa2gIR0Bedti2DxsmdX2UKGgGR8BUgAAAAAAAaAdLU2gIR0Bed5ZwGW2PdX2UKGgGR8BVAAAAAAAAaAdLVWgIR0Begdovi97GdX2UKGgGR8BUAAAAAAAAaAdLUWgIR0Beghjvuw5edX2UKGgGR8BVAAAAAAAAaAdLVWgIR0BejcFyJbdKdX2UKGgGR8BZQAAAAAAAaAdLZmgIR0BekFM/QjUvdX2UKGgGR8BRgAAAAAAAaAdLR2gIR0BelxA0Kqn4dX2UKGgGR8BTAAAAAAAAaAdLTWgIR0BemjcuanaWdX2UKGgGR8BRwAAAAAAAaAdLSGgIR0BeoC+cpb2UdX2UKGgGR8BRgAAAAAAAaAdLR2gIR0Beo3jIaLn+dX2UKGgGR8BXAAAAAAAAaAdLXWgIR0Beq/qkdmxudX2UKGgGR8BWQAAAAAAAaAdLWmgIR0BermsNlRP5dX2UKGgGR8BUAAAAAAAAaAdLUWgIR0BetV9Sde6adX2UKGgGR8BRQAAAAAAAaAdLRmgIR0BetpHVf/m1dX2UKGgGR8BPgAAAAAAAaAdLQGgIR0BevnbM5fdAdX2UKGgGR8BfQAAAAAAAaAdLfmgIR0BeyXeWOZLJdX2UKGgGR8BVAAAAAAAAaAdLVWgIR0BeyzvVmSQpdX2UKGgGR8BUAAAAAAAAaAdLUWgIR0Be1CLMs6JZdX2UKGgGR8BRgAAAAAAAaAdLR2gIR0Be1JO32EkCdX2UKGgGR8BSgAAAAAAAaAdLS2gIR0Be3ZjQRf4RdX2UKGgGR8BRgAAAAAAAaAdLR2gIR0Be3YCdSVGDdX2UKGgGR8BSQAAAAAAAaAdLSmgIR0BfEJhnanJldX2UKGgGR8BTgAAAAAAAaAdLT2gIR0BfEViay8jBdX2UKGgGR8BTAAAAAAAAaAdLTWgIR0BfHFYZEUj+dX2UKGgGR8BUwAAAAAAAaAdLVGgIR0BfHLwOOKfndX2UKGgGR8BRwAAAAAAAaAdLSGgIR0BfJqlk6LfldX2UKGgGR8BVgAAAAAAAaAdLV2gIR0BfKFXV9Wp7dX2UKGgGR8BTQAAAAAAAaAdLTmgIR0BfMPtpmEoOdX2UKGgGR8BVAAAAAAAAaAdLVWgIR0BfM2M85jpcdX2UKGgGR8BWwAAAAAAAaAdLXGgIR0BfPFbFCLMtdX2UKGgGR8BYgAAAAAAAaAdLY2gIR0BfP7iEQGwBdX2UKGgGR8BXgAAAAAAAaAdLX2gIR0BfSVstTUAldX2UKGgGR8BXgAAAAAAAaAdLX2gIR0BfTq4hEBsAdX2UKGgGR8BVAAAAAAAAaAdLVWgIR0BfWB4IKMNudX2UKGgGR8BSQAAAAAAAaAdLSmgIR0BfWf0RODaodX2UKGgGR8BUgAAAAAAAaAdLU2gIR0BfYmeDnNgSdX2UKGgGR8BXQAAAAAAAaAdLXmgIR0BfZbOeJ53UdX2UKGgGR8BQwAAAAAAAaAdLRGgIR0BfayKrJbMYdX2UKGgGR8BWAAAAAAAAaAdLWWgIR0Bfcbpu/DcedX2UKGgGR8BSQAAAAAAAaAdLSmgIR0BfdVvQ4S6EdX2UKGgGR8BTQAAAAAAAaAdLTmgIR0Bfe66OHWSVdX2UKGgGR8BWgAAAAAAAaAdLW2gIR0BfgLiVB2OidX2UKGgGR8BSQAAAAAAAaAdLSmgIR0BfhNWZJCjUdX2UKGgGR8BUwAAAAAAAaAdLVGgIR0Bfitv863iJdX2UKGgGR8BUQAAAAAAAaAdLUmgIR0BfjswYcebNdX2UKGgGR8BUQAAAAAAAaAdLUmgIR0BfuGY8dPtVdX2UKGgGR8BTQAAAAAAAaAdLTmgIR0Bfu+yquKXOdX2UKGgGR8BSQAAAAAAAaAdLSmgIR0BfwVklNUOvdX2UKGgGR8BTQAAAAAAAaAdLTmgIR0BfxSo0hvBKdX2UKGgGR8BWAAAAAAAAaAdLWWgIR0BfzeMQ2/BWdX2UKGgGR8BQAAAAAAAAaAdLQWgIR0Bfztr9ETg3dX2UKGgGR8BUAAAAAAAAaAdLUWgIR0Bf18dLg4wRdX2UKGgGR8BVQAAAAAAAaAdLVmgIR0Bf2VS0jTrndX2UKGgGR8BTgAAAAAAAaAdLT2gIR0Bf4cjmjj7zdX2UKGgGR8BRgAAAAAAAaAdLR2gIR0Bf4nxFy7wsdX2UKGgGR8BRgAAAAAAAaAdLR2gIR0Bf753cHnlodX2UKGgGR8BTgAAAAAAAaAdLT2gIR0Bf8XSncclxdX2UKGgGR8BWAAAAAAAAaAdLWWgIR0Bf/fAsTWXkdX2UKGgGR8BUgAAAAAAAaAdLU2gIR0Bf/86V+qiodX2UKGgGR8BRwAAAAAAAaAdLSGgIR0BgBesPrfLtdX2UKGgGR8BVAAAAAAAAaAdLVWgIR0BgBlUOuq3mdX2UKGgGR8BRwAAAAAAAaAdLSGgIR0BgCvDcdo38dX2UKGgGR8BVAAAAAAAAaAdLVWgIR0BgDCN4qwyJdX2UKGgGR8BVAAAAAAAAaAdLVWgIR0BgEFS619fDdX2UKGgGR8BTgAAAAAAAaAdLT2gIR0BgFTK7qY7adX2UKGgGR8BPgAAAAAAAaAdLQGgIR0BgGW9Htnf3dX2UKGgGR8BrYAAAAAAAaAdL3GgIR0BgGjLt/nW8dX2UKGgGR8BPAAAAAAAAaAdLP2gIR0BgHj8gpz91dX2UKGgGR8BTwAAAAAAAaAdLUGgIR0BgHqUA1ejVdX2UKGgGR8BTQAAAAAAAaAdLTmgIR0BgOcnRb8m8dX2UKGgGR8BRwAAAAAAAaAdLSGgIR0BgQZm7J4jbdX2UKGgGR8BlYAAAAAAAaAdLrGgIR0BgRKB/ZuhsdX2UKGgGR8BVAAAAAAAAaAdLVWgIR0BgSsS5AhStdX2UKGgGR8BTAAAAAAAAaAdLTWgIR0BgTUurZJ05dX2UKGgGR8BYgAAAAAAAaAdLY2gIR0BgVTb+Lm6odX2UKGgGR8BTgAAAAAAAaAdLT2gIR0BgVU/6fra/dX2UKGgGR8BRwAAAAAAAaAdLSGgIR0BgXSYRdyDJdX2UKGgGR8BSQAAAAAAAaAdLSmgIR0BgXVPBSDRMdX2UKGgGR8BRAAAAAAAAaAdLRWgIR0BgZPtMPBi1dX2UKGgGR8BTQAAAAAAAaAdLTmgIR0BgZdXvH93sdX2UKGgGR8BTgAAAAAAAaAdLT2gIR0Bga4rvsqrjdX2UKGgGR8BVAAAAAAAAaAdLVWgIR0BgbPFDOTq0dX2UKGgGR8BRQAAAAAAAaAdLRmgIR0BgcoLXtjTbdX2UKGgGR8BVgAAAAAAAaAdLV2gIR0BgdM5MlC1JdX2UKGgGR8BWwAAAAAAAaAdLXGgIR0BgeQ5BC2MLdX2UKGgGR8BVgAAAAAAAaAdLV2gIR0Bgeunfl6qsdX2UKGgGR8BUAAAAAAAAaAdLUWgIR0Bgfv5ckdFOdX2UKGgGR8BRgAAAAAAAaAdLR2gIR0BghYkRjBl+dX2UKGgGR8Bj4AAAAAAAaAdLoGgIR0Bgh/7m+0w8dX2UKGgGR8BRgAAAAAAAaAdLR2gIR0BgpOG7BfrsdX2UKGgGR8BRQAAAAAAAaAdLRmgIR0Bgp2ktVaOhdX2UKGgGR8BVQAAAAAAAaAdLVmgIR0BgrbuUliSadWUu"
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 49,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.99,
|
81 |
+
"gae_lambda": 0.95,
|
82 |
+
"ent_coef": 0.0,
|
83 |
+
"vf_coef": 0.0,
|
84 |
+
"max_grad_norm": 0.0,
|
85 |
+
"normalize_advantage": true,
|
86 |
+
"batch_size": 128,
|
87 |
+
"cg_max_steps": 15,
|
88 |
+
"cg_damping": 0.1,
|
89 |
+
"line_search_shrinking_factor": 0.8,
|
90 |
+
"line_search_max_iter": 10,
|
91 |
+
"target_kl": 0.01,
|
92 |
+
"n_critic_updates": 10,
|
93 |
+
"sub_sampling_factor": 1
|
94 |
+
}
|
trpo-Acrobot-v1/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60ed48b0b7f1edd7d28b4f89b98db87bec8501e41e6f5ec52da0fa2d3726b6a5
|
3 |
+
size 40705
|
trpo-Acrobot-v1/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6965379243845f9aa2ad884474ec0ca24d1575b081c938ee871d450c9ef14211
|
3 |
+
size 41921
|
trpo-Acrobot-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
|
trpo-Acrobot-v1/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
|
vec_normalize.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76e86fd72ae428e1d8a85e71617153a41635412d33f2f6202e518a8519f49d43
|
3 |
+
size 4371
|