Hugging Face's logo

yykakui
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
yykakui commited on
Commit
b0b5bf1
•
1 Parent(s): 98c1e4c

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +2 -2
  2. args.yml +2 -2
  3. config.yml +1 -1
  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: 268.50 +/- 78.17
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 100000.0),
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: 660.00 +/- 262.55
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -20,7 +20,7 @@
20
  - - hyperparams
21
  - null
22
  - - log_folder
23
- - logs/
24
  - - log_interval
25
  - -1
26
  - - max_total_trials
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 3339054740
60
  - - storage
61
  - null
62
  - - study_name
 
20
  - - hyperparams
21
  - null
22
  - - log_folder
23
+ - los/
24
  - - log_interval
25
  - -1
26
  - - max_total_trials
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 2809033962
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 1000000.0
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 sha256:49aacd3969be4348721b6f91b44c6f020ea25bc6ea1f3cbc28e12ded15a110c9
3
- size 13715667
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd6eba80c66074496de1c01bdc93d09b9cb11e668f50725150a5485902f1419f
3
+ size 27220728
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 sha256:215ea7d8898faa9284464c7109532cf36390d330fccab8d77eeba20628a32876
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1a4f1865d2303f6b866be30eef724c86e0d4acd4406f3ba9e69665132445203
3
+ size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7268ca4c27b7d67742162c72c7b249831e1856bb674c7ffe292bcdaec891570
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c53ee59ba0f791d1b14cf35864b6dbb3cdfecd55450f0972cee419ac35d0c4
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5088964ec35c06c97c1ec6428030f6ca02cea989b62b7404112500c51a53e6d
3
- size 278699
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03886c6d404181393263c16fdd1dbc96090fa0a2acc9faa504c158a8cf879ee1
3
+ size 275768
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 268.5, "std_reward": 78.16808811785025, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-07-23T11:06:03.665104"}
 
1
+ {"mean_reward": 660.0, "std_reward": 262.55475619382713, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-07-24T02:22:04.561883"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7f173ebd8edb008629690c2085f997ffdffa80ff570bcd6645f5bcfdc5d4a0e
3
- size 5937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e524d2c4f0de1ce7cd2a147c5f53e81fad8199d37f55e858015c7af1b8059dca
3
+ size 36226