Hugging Face's logo

plegg
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
plegg commited on
Commit
a04b9d4
·
1 Parent(s): 0a71a4d

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -3
  2. args.yml +1 -1
  3. config.yml +2 -2
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  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: 14.50 +/- 12.34
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -70,9 +70,9 @@ OrderedDict([('batch_size', 32),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 1000),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 100000),
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: 573.00 +/- 170.12
20
  name: mean_reward
21
  verified: false
22
  ---
 
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', 1000000),
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
- - 3064922676
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1353891345
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 1000
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 1000000
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:f8fb43e155dda919c844f48d595b331e1afedeaf38354f14cdead2c613b65faf
3
- size 13719746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84291f6d3cc9f31398f4ae8b7ae9940e908160ed784376d120569e91de907f13
3
+ size 27224807
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 sha256:295ba74feb76634aebdb7a23fef4dccc5e8b501a1bb102dc116367e9170c6ded
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c9c6578394a05dc198770cdf05cade72f4d5b6997020a36e45aff16d513169
3
+ size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8102836d25fe54bb451bfb4dfb921c615306cbfe752dbfbbf85ec0187f5b7f87
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13cfe38fc69d6513a806abd9e8068880739192a7abfb33635a60ab2f7081467c
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fed103c47817f3f94ef4564da11c292e2891460f38d04aed7c8ce7eca6e1ea9
3
- size 275554
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29fed27e6a7f691225944b56076904758c97bc0f9a262cc44986d8983a89081a
3
+ size 238160
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 14.5, "std_reward": 12.338962679253067, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T22:59:04.840432"}
 
1
+ {"mean_reward": 573.0, "std_reward": 170.12054549642144, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-01T23:52:12.808653"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0edc3322a23d191dacbf0fae8d5d7f5e9acfaf66dc52460e2110f28bf2fd545d
3
- size 5880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31e13811a07b86e260fa63b007eb4ebd83b9e1734b4d77d358c72ef63ee75be2
3
+ size 37159