Hugging Face's logo

CreativeEvolution
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
CreativeEvolution commited on
Commit
5d601c5
•
1 Parent(s): 0cd96e4

Second commit

Browse files
Files changed (11) hide show
  1. README.md +2 -2
  2. args.yml +3 -3
  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: 700.50 +/- 276.46
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: 799.50 +/- 272.11
20
  name: mean_reward
21
  verified: false
22
  ---
 
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
+ ('n_timesteps', 4000000.0),
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
@@ -50,11 +50,11 @@
50
  - - sampler
51
  - tpe
52
  - - save_freq
53
- - -1
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2325814001
58
  - - storage
59
  - null
60
  - - study_name
 
18
  - - hyperparams
19
  - null
20
  - - log_folder
21
+ - /content/drive/Othercomputers/Laptop/Python/HuggingFace_DeepRL/unit_3_optimization/logs/
22
  - - log_interval
23
  - -1
24
  - - max_total_trials
 
50
  - - sampler
51
  - tpe
52
  - - save_freq
53
+ - 300000
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2648392649
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
+ - 4000000.0
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 sha256:978997c5299a213111392326e6a145e4452dbd20dd927a8cf32a6c8c02c0124a
3
- size 27224788
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b723d99c2096b015194b6030696c594ea029b6baf022892033815103cd46ed
3
+ size 27224292
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:e4a161744f49eb1bb88a3d10e6c99486cb713f64dd6fbc31207f77cb31e44b3d
3
- size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:477ad5247c3b3b9cfd1a80e26e5bb6f66c6175cf30749337422ad5a44c0c93a8
3
+ size 13505419
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2830a63cbc5aa58a318b6403d9a6def873b4fb3ef936db9d48b6ae805ed89505
3
- size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e06999d6906da995e8824f80bb62778f86f029d334f7f2249fbf67c2a4d877a
3
+ size 13504745
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,6 +2,6 @@ OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
2
  Python: 3.8.16
3
  Stable-Baselines3: 1.6.2
4
  PyTorch: 1.13.0+cu116
5
- GPU Enabled: True
6
  Numpy: 1.21.6
7
  Gym: 0.21.0
 
2
  Python: 3.8.16
3
  Stable-Baselines3: 1.6.2
4
  PyTorch: 1.13.0+cu116
5
+ GPU Enabled: False
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:fc0b3c3c2f8d11958a05bdf5aa36402c2440fe603cf461f2aaa47f707d980f59
3
- size 251121
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ee4dd87183fc9dc9979ac7e7e088f9c28657b8b50a4c6aa96496781892ec91
3
+ size 189041
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 700.5, "std_reward": 276.46383126911917, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-20T13:13:27.268983"}
 
1
+ {"mean_reward": 799.5, "std_reward": 272.10705613783705, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-21T20:09:38.182375"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cc6186156a5dd91c6c9b590bec9a35ff5afae4d0655971107a2a2d8f4785148
3
- size 36555
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de102a5784f27e0471a905962dcf5a833227d1665ff741b20b54491240d3f6b8
3
+ size 10490