Hugging Face's logo

RegisGraptin
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
RegisGraptin commited on
Commit
f3b1693
·
1 Parent(s): 22dedce

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +5 -5
  2. args.yml +1 -1
  3. config.yml +4 -4
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. replay.mp4 +2 -2
  9. results.json +1 -1
  10. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 99.50 +/- 41.74
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,17 +62,17 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 256),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
- ('exploration_final_eps', 0.1),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.01),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 692.00 +/- 164.29
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 32),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
+ ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 1900000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2736754923
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2035377547
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,12 +1,12 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 256
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
- - 0.1
10
  - - exploration_fraction
11
  - 0.1
12
  - - frame_stack
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.01
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
+ - 0.01
10
  - - exploration_fraction
11
  - 0.1
12
  - - frame_stack
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 1900000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f56313e6f54eaaa49a39d802fc42145636c42c7d84b469b53060e8b9aa5f2969
3
- size 27224808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38e6bffbcb4d1d67291b292b1e5d92ff1e823771453b608d43eff175d45457b1
3
+ size 27224809
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cf2c1a9e838dccc8594328c610311cfe5251d77f8917a8f0158af6d3404dc65
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99473c569251182ce156048138211a55199d36c27e4828f8f893e69cee9840e5
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2536481d064d825e37bf050b9e541178266d536698258c8a48548411768d8bff
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821185307e735d365d6d4658e9c46bee05ad08898d267d6af8669b1cb7be8d34
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:987650ebaa485c87159d44af7e9209ad191da9d4da3f9e461c9be45ccc055801
3
- size 258408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18aca1d54e461513fce6daf90a075e988696de505d7253a018fd1979511b1923
3
+ size 206175
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 99.5, "std_reward": 41.740268326880695, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-07T12:17:51.357103"}
 
1
+ {"mean_reward": 692.0, "std_reward": 164.28937884111681, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-10T10:11:07.367176"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21ae213d77f63e86325c96cc60ed595efac9b665b74213f3b6218ab8ab343565
3
- size 41806
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a346ae5a733dbe10d465c2dfd6aec017a09cdc8ae2827157cf263c11356225
3
+ size 61678