Hugging Face's logo

bsmith0430
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
bsmith0430 commited on
Commit
d1674fa
·
1 Parent(s): c804d33

Initial commit

Browse files
Files changed (11) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  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 +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
  9. replay.mp4 +2 -2
  10. results.json +1 -1
  11. 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: 15.50 +/- 12.54
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', 100000.0),
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: 617.00 +/- 149.52
20
  name: mean_reward
21
  verified: false
22
  ---
 
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),
args.yml CHANGED
@@ -52,7 +52,7 @@
52
  - - save_replay_buffer
53
  - false
54
  - - seed
55
- - 3979697793
56
  - - storage
57
  - null
58
  - - study_name
 
52
  - - save_replay_buffer
53
  - false
54
  - - seed
55
+ - 2091252674
56
  - - storage
57
  - null
58
  - - 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:e9eff5566de54e4e8ddcef3a9e163d2e7db8f56cb14f7a877c0d9b0462f82a27
3
- size 13719706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82b31a3d223625e571913cd5fbf3dbdb3b883342718690d1e4542c11875e60f6
3
+ size 27224958
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 sha256:71a21ae67866ddb856ecbb70c8ba0e04af200cc5da53fbcb90e773d87e996b31
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:509072d4f6e16c2ded2012dcbf9e97059a581109101ca70ff31b9d8d0c7561a7
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:ca618e809f0b266235e612d512c442e5094ee55c23d8f288ab527522da1782b2
3
- size 13504745
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b6d292de35f2582781743afd3a8095a9b5caa771ddac79dfba7c5425a093990
3
+ size 13504937
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,6 +2,6 @@ OS: Linux-5.10.133+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Fri Aug 26 08:44:51 U
2
  Python: 3.7.15
3
  Stable-Baselines3: 1.6.2
4
  PyTorch: 1.12.1+cu113
5
- GPU Enabled: False
6
  Numpy: 1.21.6
7
  Gym: 0.21.0
 
2
  Python: 3.7.15
3
  Stable-Baselines3: 1.6.2
4
  PyTorch: 1.12.1+cu113
5
+ GPU Enabled: True
6
  Numpy: 1.21.6
7
  Gym: 0.21.0
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d4afaddf633990f3d270cf9e169f40ac375b39e821b996f71f99ba9161b17f7
3
- size 273553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c47cf27874c36f0becd9566949fb58d19cdd9c6274116f2e6f7154ff01734e4e
3
+ size 189550
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 15.5, "std_reward": 12.539936203984453, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-11-30T12:36:12.288669"}
 
1
+ {"mean_reward": 617.0, "std_reward": 149.51922953252534, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-11-30T14:21:37.043330"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f995a20d33bb3be1d2c2e9de8b0805ca363115e20540394e0e9b36a6f0f8da5a
3
- size 5781
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f6597e11a1317e45387abd6c4f8dc7e67b3e38b51d6faeeafadd5b2a31d861
3
+ size 37709