Quentin Gallouédec
commited on
Commit
•
257d83f
1
Parent(s):
18e254a
Initial commit
Browse files- .gitattributes +1 -0
- README.md +75 -0
- args.yml +83 -0
- config.yml +17 -0
- ddpg-CartpoleSparseDMC-v0.zip +3 -0
- ddpg-CartpoleSparseDMC-v0/_stable_baselines3_version +1 -0
- ddpg-CartpoleSparseDMC-v0/actor.optimizer.pth +3 -0
- ddpg-CartpoleSparseDMC-v0/critic.optimizer.pth +3 -0
- ddpg-CartpoleSparseDMC-v0/data +137 -0
- ddpg-CartpoleSparseDMC-v0/policy.pth +3 -0
- ddpg-CartpoleSparseDMC-v0/pytorch_variables.pth +3 -0
- ddpg-CartpoleSparseDMC-v0/system_info.txt +7 -0
- env_kwargs.yml +1 -0
- replay.mp4 +3 -0
- results.json +1 -0
- train_eval_metrics.zip +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- CartpoleSparseDMC-v0
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: DDPG
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: CartpoleSparseDMC-v0
|
16 |
+
type: CartpoleSparseDMC-v0
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 1000.00 +/- 0.00
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **DDPG** Agent playing **CartpoleSparseDMC-v0**
|
25 |
+
This is a trained model of a **DDPG** agent playing **CartpoleSparseDMC-v0**
|
26 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
|
27 |
+
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
|
28 |
+
|
29 |
+
The RL Zoo is a training framework for Stable Baselines3
|
30 |
+
reinforcement learning agents,
|
31 |
+
with hyperparameter optimization and pre-trained agents included.
|
32 |
+
|
33 |
+
## Usage (with SB3 RL Zoo)
|
34 |
+
|
35 |
+
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
|
36 |
+
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
|
37 |
+
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
38 |
+
|
39 |
+
Install the RL Zoo (with SB3 and SB3-Contrib):
|
40 |
+
```bash
|
41 |
+
pip install rl_zoo3
|
42 |
+
```
|
43 |
+
|
44 |
+
```
|
45 |
+
# Download model and save it into the logs/ folder
|
46 |
+
python -m rl_zoo3.load_from_hub --algo ddpg --env CartpoleSparseDMC-v0 -orga qgallouedec -f logs/
|
47 |
+
python -m rl_zoo3.enjoy --algo ddpg --env CartpoleSparseDMC-v0 -f logs/
|
48 |
+
```
|
49 |
+
|
50 |
+
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
|
51 |
+
```
|
52 |
+
python -m rl_zoo3.load_from_hub --algo ddpg --env CartpoleSparseDMC-v0 -orga qgallouedec -f logs/
|
53 |
+
python -m rl_zoo3.enjoy --algo ddpg --env CartpoleSparseDMC-v0 -f logs/
|
54 |
+
```
|
55 |
+
|
56 |
+
## Training (with the RL Zoo)
|
57 |
+
```
|
58 |
+
python -m rl_zoo3.train --algo ddpg --env CartpoleSparseDMC-v0 -f logs/
|
59 |
+
# Upload the model and generate video (when possible)
|
60 |
+
python -m rl_zoo3.push_to_hub --algo ddpg --env CartpoleSparseDMC-v0 -f logs/ -orga qgallouedec
|
61 |
+
```
|
62 |
+
|
63 |
+
## Hyperparameters
|
64 |
+
```python
|
65 |
+
OrderedDict([('batch_size', 64),
|
66 |
+
('gamma', 0.99),
|
67 |
+
('learning_rate', 0.0001),
|
68 |
+
('n_timesteps', 1000000.0),
|
69 |
+
('noise_std', 0.3),
|
70 |
+
('noise_type', 'ornstein-uhlenbeck'),
|
71 |
+
('policy', 'MlpPolicy'),
|
72 |
+
('policy_kwargs',
|
73 |
+
'dict(net_arch=dict(pi=[300, 200], qf=[400, 300]))'),
|
74 |
+
('normalize', False)])
|
75 |
+
```
|
args.yml
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - algo
|
3 |
+
- ddpg
|
4 |
+
- - conf_file
|
5 |
+
- null
|
6 |
+
- - device
|
7 |
+
- auto
|
8 |
+
- - env
|
9 |
+
- CartpoleSparseDMC-v0
|
10 |
+
- - env_kwargs
|
11 |
+
- null
|
12 |
+
- - eval_episodes
|
13 |
+
- 20
|
14 |
+
- - eval_freq
|
15 |
+
- 25000
|
16 |
+
- - gym_packages
|
17 |
+
- []
|
18 |
+
- - hyperparams
|
19 |
+
- null
|
20 |
+
- - log_folder
|
21 |
+
- logs
|
22 |
+
- - log_interval
|
23 |
+
- -1
|
24 |
+
- - max_total_trials
|
25 |
+
- null
|
26 |
+
- - n_eval_envs
|
27 |
+
- 5
|
28 |
+
- - n_evaluations
|
29 |
+
- null
|
30 |
+
- - n_jobs
|
31 |
+
- 1
|
32 |
+
- - n_startup_trials
|
33 |
+
- 10
|
34 |
+
- - n_timesteps
|
35 |
+
- -1
|
36 |
+
- - n_trials
|
37 |
+
- 500
|
38 |
+
- - no_optim_plots
|
39 |
+
- false
|
40 |
+
- - num_threads
|
41 |
+
- -1
|
42 |
+
- - optimization_log_path
|
43 |
+
- null
|
44 |
+
- - optimize_hyperparameters
|
45 |
+
- false
|
46 |
+
- - progress
|
47 |
+
- false
|
48 |
+
- - pruner
|
49 |
+
- median
|
50 |
+
- - sampler
|
51 |
+
- tpe
|
52 |
+
- - save_freq
|
53 |
+
- -1
|
54 |
+
- - save_replay_buffer
|
55 |
+
- false
|
56 |
+
- - seed
|
57 |
+
- 1516962314
|
58 |
+
- - storage
|
59 |
+
- null
|
60 |
+
- - study_name
|
61 |
+
- null
|
62 |
+
- - tensorboard_log
|
63 |
+
- runs/CartpoleSparseDMC-v0__ddpg__1516962314__1673811016
|
64 |
+
- - track
|
65 |
+
- true
|
66 |
+
- - trained_agent
|
67 |
+
- ''
|
68 |
+
- - truncate_last_trajectory
|
69 |
+
- true
|
70 |
+
- - uuid
|
71 |
+
- false
|
72 |
+
- - vec_env
|
73 |
+
- dummy
|
74 |
+
- - verbose
|
75 |
+
- 1
|
76 |
+
- - wandb_entity
|
77 |
+
- qgallouedec
|
78 |
+
- - wandb_project_name
|
79 |
+
- dmc
|
80 |
+
- - wandb_tags
|
81 |
+
- []
|
82 |
+
- - yaml_file
|
83 |
+
- null
|
config.yml
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - batch_size
|
3 |
+
- 64
|
4 |
+
- - gamma
|
5 |
+
- 0.99
|
6 |
+
- - learning_rate
|
7 |
+
- 0.0001
|
8 |
+
- - n_timesteps
|
9 |
+
- 1000000.0
|
10 |
+
- - noise_std
|
11 |
+
- 0.3
|
12 |
+
- - noise_type
|
13 |
+
- ornstein-uhlenbeck
|
14 |
+
- - policy
|
15 |
+
- MlpPolicy
|
16 |
+
- - policy_kwargs
|
17 |
+
- dict(net_arch=dict(pi=[300, 200], qf=[400, 300]))
|
ddpg-CartpoleSparseDMC-v0.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08ad3d8791d843fc0d65ae0d5c25f0c41df958ef56c7d706fb2ee58481371ef3
|
3 |
+
size 3011992
|
ddpg-CartpoleSparseDMC-v0/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
ddpg-CartpoleSparseDMC-v0/actor.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68a55cec567562983369724907a094b80aec7bd7aafd3b4028da8ee5232f163b
|
3 |
+
size 502319
|
ddpg-CartpoleSparseDMC-v0/critic.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c88e673bdf3d67fe70cb939e68b99f4139787d0269669adc1343535db418852
|
3 |
+
size 991855
|
ddpg-CartpoleSparseDMC-v0/data
ADDED
@@ -0,0 +1,137 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMCVREM1BvbGljeZSTlC4=",
|
5 |
+
"__module__": "stable_baselines3.td3.policies",
|
6 |
+
"__doc__": "\n Policy class (with both actor and critic) for TD3.\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 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 TD3Policy.__init__ at 0x132b98280>",
|
8 |
+
"_build": "<function TD3Policy._build at 0x132b98310>",
|
9 |
+
"_get_constructor_parameters": "<function TD3Policy._get_constructor_parameters at 0x132b983a0>",
|
10 |
+
"make_actor": "<function TD3Policy.make_actor at 0x132b98430>",
|
11 |
+
"make_critic": "<function TD3Policy.make_critic at 0x132b984c0>",
|
12 |
+
"forward": "<function TD3Policy.forward at 0x132b98550>",
|
13 |
+
"_predict": "<function TD3Policy._predict at 0x132b985e0>",
|
14 |
+
"set_training_mode": "<function TD3Policy.set_training_mode at 0x132b98670>",
|
15 |
+
"__abstractmethods__": "frozenset()",
|
16 |
+
"_abc_impl": "<_abc._abc_data object at 0x132b92c40>"
|
17 |
+
},
|
18 |
+
"verbose": 1,
|
19 |
+
"policy_kwargs": {
|
20 |
+
"net_arch": {
|
21 |
+
"pi": [
|
22 |
+
300,
|
23 |
+
200
|
24 |
+
],
|
25 |
+
"qf": [
|
26 |
+
400,
|
27 |
+
300
|
28 |
+
]
|
29 |
+
},
|
30 |
+
"n_critics": 1
|
31 |
+
},
|
32 |
+
"observation_space": {
|
33 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
34 |
+
":serialized:": "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",
|
35 |
+
"dtype": "float32",
|
36 |
+
"_shape": [
|
37 |
+
5
|
38 |
+
],
|
39 |
+
"low": "[-inf -inf -inf -inf -inf]",
|
40 |
+
"high": "[inf inf inf inf inf]",
|
41 |
+
"bounded_below": "[False False False False False]",
|
42 |
+
"bounded_above": "[False False False False False]",
|
43 |
+
"_np_random": "RandomState(MT19937)"
|
44 |
+
},
|
45 |
+
"action_space": {
|
46 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
47 |
+
":serialized:": "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",
|
48 |
+
"dtype": "float32",
|
49 |
+
"_shape": [
|
50 |
+
1
|
51 |
+
],
|
52 |
+
"low": "[-1.]",
|
53 |
+
"high": "[1.]",
|
54 |
+
"bounded_below": "[ True]",
|
55 |
+
"bounded_above": "[ True]",
|
56 |
+
"_np_random": "RandomState(MT19937)"
|
57 |
+
},
|
58 |
+
"n_envs": 1,
|
59 |
+
"num_timesteps": 1000000,
|
60 |
+
"_total_timesteps": 1000000,
|
61 |
+
"_num_timesteps_at_start": 0,
|
62 |
+
"seed": 0,
|
63 |
+
"action_noise": {
|
64 |
+
":type:": "<class 'stable_baselines3.common.noise.OrnsteinUhlenbeckActionNoise'>",
|
65 |
+
":serialized:": "gAWVVQEAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5ub2lzZZSMHE9ybnN0ZWluVWhsZW5iZWNrQWN0aW9uTm9pc2WUk5QpgZR9lCiMBl90aGV0YZRHP8MzMzMzMzOMA19tdZSMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlIwGX3NpZ21hlGgJKJYIAAAAAAAAADMzMzMzM9M/lGgQSwGFlGgUdJRSlIwDX2R0lEc/hHrhR64Ue4wNaW5pdGlhbF9ub2lzZZROjApub2lzZV9wcmV2lGgJKJYIAAAAAAAAAAAAAAAAAAAAlGgQSwGFlGgUdJRSlHViLg==",
|
66 |
+
"_theta": 0.15,
|
67 |
+
"_mu": "[0.]",
|
68 |
+
"_sigma": "[0.3]",
|
69 |
+
"_dt": 0.01,
|
70 |
+
"initial_noise": null,
|
71 |
+
"noise_prev": "[0.]"
|
72 |
+
},
|
73 |
+
"start_time": 1673811020944898084,
|
74 |
+
"learning_rate": {
|
75 |
+
":type:": "<class 'function'>",
|
76 |
+
":serialized:": "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"
|
77 |
+
},
|
78 |
+
"tensorboard_log": "runs/CartpoleSparseDMC-v0__ddpg__1516962314__1673811016/CartpoleSparseDMC-v0",
|
79 |
+
"lr_schedule": {
|
80 |
+
":type:": "<class 'function'>",
|
81 |
+
":serialized:": "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"
|
82 |
+
},
|
83 |
+
"_last_obs": null,
|
84 |
+
"_last_episode_starts": {
|
85 |
+
":type:": "<class 'numpy.ndarray'>",
|
86 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
87 |
+
},
|
88 |
+
"_last_original_obs": {
|
89 |
+
":type:": "<class 'numpy.ndarray'>",
|
90 |
+
":serialized:": "gAWViQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYUAAAAAAAAAHQslz5ZuH8/NXs/vcDVkr7YUww+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwWGlIwBQ5R0lFKULg=="
|
91 |
+
},
|
92 |
+
"_episode_num": 1000,
|
93 |
+
"use_sde": false,
|
94 |
+
"sde_sample_freq": -1,
|
95 |
+
"_current_progress_remaining": 0.0,
|
96 |
+
"ep_info_buffer": {
|
97 |
+
":type:": "<class 'collections.deque'>",
|
98 |
+
":serialized:": "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"
|
99 |
+
},
|
100 |
+
"ep_success_buffer": {
|
101 |
+
":type:": "<class 'collections.deque'>",
|
102 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
103 |
+
},
|
104 |
+
"_n_updates": 1000000,
|
105 |
+
"buffer_size": 1,
|
106 |
+
"batch_size": 64,
|
107 |
+
"learning_starts": 100,
|
108 |
+
"tau": 0.005,
|
109 |
+
"gamma": 0.99,
|
110 |
+
"gradient_steps": -1,
|
111 |
+
"optimize_memory_usage": false,
|
112 |
+
"replay_buffer_class": {
|
113 |
+
":type:": "<class 'abc.ABCMeta'>",
|
114 |
+
":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
115 |
+
"__module__": "stable_baselines3.common.buffers",
|
116 |
+
"__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: PyTorch 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 Cannot be used in combination with handle_timeout_termination.\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 ",
|
117 |
+
"__init__": "<function ReplayBuffer.__init__ at 0x132b96dd0>",
|
118 |
+
"add": "<function ReplayBuffer.add at 0x132b96e60>",
|
119 |
+
"sample": "<function ReplayBuffer.sample at 0x132b96ef0>",
|
120 |
+
"_get_samples": "<function ReplayBuffer._get_samples at 0x132b96f80>",
|
121 |
+
"__abstractmethods__": "frozenset()",
|
122 |
+
"_abc_impl": "<_abc._abc_data object at 0x132746140>"
|
123 |
+
},
|
124 |
+
"replay_buffer_kwargs": {},
|
125 |
+
"train_freq": {
|
126 |
+
":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
|
127 |
+
":serialized:": "gAWVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMB2VwaXNvZGWUhZRSlIaUgZQu"
|
128 |
+
},
|
129 |
+
"use_sde_at_warmup": false,
|
130 |
+
"policy_delay": 1,
|
131 |
+
"target_noise_clip": 0.0,
|
132 |
+
"target_policy_noise": 0.1,
|
133 |
+
"actor_batch_norm_stats": [],
|
134 |
+
"critic_batch_norm_stats": [],
|
135 |
+
"actor_batch_norm_stats_target": [],
|
136 |
+
"critic_batch_norm_stats_target": []
|
137 |
+
}
|
ddpg-CartpoleSparseDMC-v0/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7d63407ebf7a74d09be50b70ecd61f5298a245e6f3fa23fdbc62bc1ce325f99
|
3 |
+
size 1492509
|
ddpg-CartpoleSparseDMC-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
|
ddpg-CartpoleSparseDMC-v0/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: macOS-13.0.1-arm64-arm-64bit Darwin Kernel Version 22.1.0: Sun Oct 9 20:14:30 PDT 2022; root:xnu-8792.41.9~2/RELEASE_ARM64_T8103
|
2 |
+
- Python: 3.10.9
|
3 |
+
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.1
|
5 |
+
- GPU Enabled: False
|
6 |
+
- Numpy: 1.24.1
|
7 |
+
- Gym: 0.21.0
|
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:e8129359534ecce558e3dcff37c6e992bef170d531d76aaf7baf13ca03a07ac8
|
3 |
+
size 115468
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 1000.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-16T08:51:40.858282"}
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ed404189d92620aec8c17c7d6aa86dabd7218c4b46eabadcdad8f050056ad6b
|
3 |
+
size 38321
|