Hugging Face's logo

peterxyz
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
peterxyz commited on
Commit
8b76453
·
1 Parent(s): ebd8077

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 +1 -1
  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: 632.50 +/- 107.92
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', 0.0001),
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: 251.00 +/- 134.31
20
  name: mean_reward
21
  verified: false
22
  ---
 
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 1e-05),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 2000000.0),
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
- - 1238156582
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 4274051109
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 1.0e-05
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 2000000.0
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 sha256:57b9179914186fd5d5048d673f7f70d494c00c1505457a2b2f53b2116f81eb48
3
  size 27224842
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cae8eb7610ce6761440d6cfd41120834a6c58a1b8d5b26551037d95678f3f1ed
3
  size 27224842
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 sha256:4fe93228ecde14e58c48cdc7fb8796f7d8602f033dcbe2506f8b5d40aed2d926
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec719b24f07f28cddea4c063c4973f2aebc1136f13633dce1c7e98e99ee5601
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2608c9da3186e761d1bed6ef894196b7e02f574eaae4f879afd06f2a9de5a199
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:515d10c273a4d6486580bb1e58fd5103e4a55f44e8df8733d2488e5a43ecb4dd
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1552efd316761a3bd4be13229f9fc30e2a3cee5a63dba59fd0266d4863c9b431
3
- size 208001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9c32fe863e48c2568e00cdde22a0e4247b42f18d79ec12334269fd220b4b6fb
3
+ size 227526
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 632.5, "std_reward": 107.9177927869172, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-23T02:49:14.955110"}
 
1
+ {"mean_reward": 251.0, "std_reward": 134.30934442547175, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-23T06:20:28.798264"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b545c7ab47694c5b0c9ace5756694be4360c9ef231e52f677f82c888e52d70aa
3
- size 35622
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9c20a05b1c0f333b631e8d9b438293ce7b58f6c992460ffe2bb9277d3c4603
3
+ size 86370