Hugging Face's logo

meln1k
/
qrdqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
meln1k commited on
Commit
c2cf758
·
1 Parent(s): 05796e4

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +1 -1
  2. args.yml +7 -7
  3. qrdqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  4. qrdqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  5. qrdqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  6. qrdqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  7. replay.mp4 +2 -2
  8. results.json +1 -1
  9. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -10,7 +10,7 @@ model-index:
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
- value: 1735.00 +/- 817.86
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
 
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
+ value: 2581.50 +/- 1151.96
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
args.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - algo
3
  - qrdqn
4
  - - device
5
- - auto
6
  - - env
7
  - SpaceInvadersNoFrameskip-v4
8
  - - env_kwargs
@@ -10,7 +10,7 @@
10
  - - eval_episodes
11
  - 5
12
  - - eval_freq
13
- - 25000
14
  - - gym_packages
15
  - []
16
  - - hyperparams
@@ -30,7 +30,7 @@
30
  - - n_startup_trials
31
  - 10
32
  - - n_timesteps
33
- - -1
34
  - - n_trials
35
  - 500
36
  - - no_optim_plots
@@ -46,17 +46,17 @@
46
  - - sampler
47
  - tpe
48
  - - save_freq
49
- - -1
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
- - 3599463833
54
  - - storage
55
  - null
56
  - - study_name
57
  - null
58
  - - tensorboard_log
59
- - runs/SpaceInvadersNoFrameskip-v4__qrdqn__3599463833__1654903955
60
  - - track
61
  - true
62
  - - trained_agent
@@ -66,7 +66,7 @@
66
  - - uuid
67
  - false
68
  - - vec_env
69
- - dummy
70
  - - verbose
71
  - 1
72
  - - wandb_entity
 
2
  - - - algo
3
  - qrdqn
4
  - - device
5
+ - cuda
6
  - - env
7
  - SpaceInvadersNoFrameskip-v4
8
  - - env_kwargs
 
10
  - - eval_episodes
11
  - 5
12
  - - eval_freq
13
+ - 100000
14
  - - gym_packages
15
  - []
16
  - - hyperparams
 
30
  - - n_startup_trials
31
  - 10
32
  - - n_timesteps
33
+ - 12000000
34
  - - n_trials
35
  - 500
36
  - - no_optim_plots
 
46
  - - sampler
47
  - tpe
48
  - - save_freq
49
+ - 100000
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
+ - 2067843970
54
  - - storage
55
  - null
56
  - - study_name
57
  - null
58
  - - tensorboard_log
59
+ - runs/SpaceInvadersNoFrameskip-v4__qrdqn__2067843970__1654945769
60
  - - track
61
  - true
62
  - - trained_agent
 
66
  - - uuid
67
  - false
68
  - - vec_env
69
+ - subproc
70
  - - verbose
71
  - 1
72
  - - wandb_entity
qrdqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbca1509177de2712c4eee4240b32bcba3ece65d9b683c079ba999e11ef44824
3
- size 37022454
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3845f344e13a6d0713aec0eeae1bfe80c5964846a35c36dcef2bdd5cefe8b93b
3
+ size 37022471
qrdqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
qrdqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa2bacb96ec64d55f1066e7fc7b0a15465669ba74fe6190df0816ff21d67224b
3
  size 18403305
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7573ae50b5cb24797da35f809d576bbb5dc92850dc8d3a478606ef0c8ea60f1e
3
  size 18403305
qrdqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48b0fdf4647e5ba9ec9b3a01b4575a4891313dad57389175f0bf8656e4494dcd
3
  size 18405545
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3917d4b306b6705fed0a81970bfbad19d2f14cf9f922ca721cffee493beac6fa
3
  size 18405545
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44921ebe9f07f8eb0ddb8ebbce8de8f7922014f2dfb39aaa956a3037dc6d881f
3
- size 162759
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d7c2d30fb654b1a777ab4113aa806b68ecd352805960a60ca6ce8520c62180e
3
+ size 206838
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 1735.0, "std_reward": 817.8630692236935, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-11T11:29:55.096517"}
 
1
+ {"mean_reward": 2581.5, "std_reward": 1151.9614793906956, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-11T21:51:32.705133"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7087ad3805c9cfd5dfd2e50d3509f63096ae159ce7898bf39262ab0b4d5dc52
3
- size 258495
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eb27c5fe4bded2ad38ca89accd50cadf4396a9958c18a456b6adcdb8b6401d2
3
+ size 255432