araffin commited on
Commit
2dbc697
1 Parent(s): 20a8fc7

Initial commit

Browse files
.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 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - SeaquestNoFrameskip-v4
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: A2C
10
+ results:
11
+ - metrics:
12
+ - type: mean_reward
13
+ value: 1706.00 +/- 95.94
14
+ name: mean_reward
15
+ task:
16
+ type: reinforcement-learning
17
+ name: reinforcement-learning
18
+ dataset:
19
+ name: SeaquestNoFrameskip-v4
20
+ type: SeaquestNoFrameskip-v4
21
+ ---
22
+
23
+ # **A2C** Agent playing **SeaquestNoFrameskip-v4**
24
+ This is a trained model of a **A2C** agent playing **SeaquestNoFrameskip-v4**
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 a2c --env SeaquestNoFrameskip-v4 -orga sb3 -f logs/
41
+ python enjoy.py --algo a2c --env SeaquestNoFrameskip-v4 -f logs/
42
+ ```
43
+
44
+ ## Training (with the RL Zoo)
45
+ ```
46
+ python train.py --algo a2c --env SeaquestNoFrameskip-v4 -f logs/
47
+ # Upload the model and generate video (when possible)
48
+ python -m utils.push_to_hub --algo a2c --env SeaquestNoFrameskip-v4 -f logs/ -orga sb3
49
+ ```
50
+
51
+ ## Hyperparameters
52
+ ```python
53
+ OrderedDict([('ent_coef', 0.01),
54
+ ('env_wrapper',
55
+ ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
56
+ ('frame_stack', 4),
57
+ ('n_envs', 16),
58
+ ('n_timesteps', 10000000.0),
59
+ ('policy', 'CnnPolicy'),
60
+ ('policy_kwargs',
61
+ 'dict(optimizer_class=RMSpropTFLike, '
62
+ 'optimizer_kwargs=dict(eps=1e-5))'),
63
+ ('vf_coef', 0.25),
64
+ ('normalize', False)])
65
+ ```
a2c-SeaquestNoFrameskip-v4.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5a910cd907d99feb426a04c57726306e09834e76e25e7065707cfc528466f4a
3
+ size 13732057
a2c-SeaquestNoFrameskip-v4/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.5.1a8
a2c-SeaquestNoFrameskip-v4/data ADDED
The diff for this file is too large to render. See raw diff
 
a2c-SeaquestNoFrameskip-v4/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c05370ae49cf24d69ac67fa3bea62ed1f278ab3d5dac4affd36e630594e9cdc1
3
+ size 6778945
a2c-SeaquestNoFrameskip-v4/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5943416146da9c986864e005105feecea6452219c7f233b524f3a912bc433b43
3
+ size 6779649
a2c-SeaquestNoFrameskip-v4/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
+ size 431
a2c-SeaquestNoFrameskip-v4/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
args.yml ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - a2c
4
+ - - env
5
+ - SeaquestNoFrameskip-v4
6
+ - - env_kwargs
7
+ - null
8
+ - - eval_episodes
9
+ - 10
10
+ - - eval_freq
11
+ - 50000
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
+ - -1
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
+ - 2655080623
44
+ - - storage
45
+ - null
46
+ - - study_name
47
+ - null
48
+ - - tensorboard_log
49
+ - ''
50
+ - - trained_agent
51
+ - ''
52
+ - - truncate_last_trajectory
53
+ - true
54
+ - - uuid
55
+ - false
56
+ - - vec_env
57
+ - dummy
58
+ - - verbose
59
+ - 1
config.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - ent_coef
3
+ - 0.01
4
+ - - env_wrapper
5
+ - - stable_baselines3.common.atari_wrappers.AtariWrapper
6
+ - - frame_stack
7
+ - 4
8
+ - - n_envs
9
+ - 16
10
+ - - n_timesteps
11
+ - 10000000.0
12
+ - - policy
13
+ - CnnPolicy
14
+ - - policy_kwargs
15
+ - dict(optimizer_class=RMSpropTFLike, optimizer_kwargs=dict(eps=1e-5))
16
+ - - vf_coef
17
+ - 0.25
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:f4537400695b60cb03cea786c275516378cee82d9ac638418388c621a65c57cc
3
+ size 162016
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 1706.0, "std_reward": 95.93747964169165, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T17:47:04.725719"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99f5b36800c35cde60fc6fde2daaa49dbfeda9643c01188704d73d433ac2cc1a
3
+ size 166733