Hugging Face's logo

sgoodfriend
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
rl-algo-impls
SpaceInvadersNoFrameskip-v4
dqn
deep-reinforcement-learning
Eval Results
Model card Files Community
sgoodfriend commited on
Commit
1ba035e
•
1 Parent(s): 3945166

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 +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: 441.00 +/- 175.25
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -67,7 +67,7 @@ OrderedDict([('batch_size', 32),
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
- ('n_timesteps', 1000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 183.00 +/- 155.47
20
  name: mean_reward
21
  verified: false
22
  ---
 
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
+ ('n_timesteps', 10000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - hyperparams
19
  - null
20
  - - log_folder
21
- - logs
22
  - - log_interval
23
  - -1
24
  - - max_total_trials
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3954862268
58
  - - storage
59
  - null
60
  - - study_name
 
18
  - - hyperparams
19
  - null
20
  - - log_folder
21
+ - logs/
22
  - - log_interval
23
  - -1
24
  - - max_total_trials
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3870387293
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 10000000.0
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 sha256:64fc7b5d139dd4e1c1132f9c59b5d1b13df2c7cbea3aa30aba391ebaf6b06c5f
3
- size 27224788
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3753431ebccbb2d31832e0aa9ead05e8a2f4d11aa41f821bb73405a013fae73
3
+ size 27224804
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 sha256:1850bc235312d065275573fdbefa75bdf29f85adb8f499ab36e29a7fef43e251
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e52947feceadf02611e96cf502092bbf60f3dbb52a7ed00d7b6d76ac36eb6ba7
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04860f5aea0e03998a1d10f6ef61b1736204b1af316ddbecac650e63ee917c7c
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:307f0f246a971abc1e0da4d1c7d83078b820874bbc83ee893b8a9fa1b6477087
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e94115abd3c1717ebb50851371e95e36011e36a0075d01c43b96e3bcf88ad8fd
3
- size 226104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:661ff3584ecf3183c00a700af0f5de0d38958d5e8fe0288c42918844bb587688
3
+ size 251326
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 441.0, "std_reward": 175.2541012358912, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-22T01:08:16.909472"}
 
1
+ {"mean_reward": 183.0, "std_reward": 155.47025438970633, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-23T19:25:00.035501"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ebbfa0d74ce1c22d2bd294002a506779aa223720fbbb8621f2a3d8d20e027b7
3
- size 36934
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c9ef35e10ed2be29d4213f1ec6941d5b3ea30b4a60678e1b8754bc225d182be
3
+ size 8627