Hugging Face's logo

DanielDsouza
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
DanielDsouza commited on
Commit
cb2783b
•
1 Parent(s): 991955d

Initial 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: 297.00 +/- 156.99
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 200000.0),
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: 239.00 +/- 181.66
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 500000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -44,17 +44,17 @@
44
  - - optimize_hyperparameters
45
  - false
46
  - - progress
47
- - false
48
  - - pruner
49
  - median
50
  - - sampler
51
  - tpe
52
  - - save_freq
53
- - -1
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1535936136
58
  - - storage
59
  - null
60
  - - study_name
 
44
  - - optimize_hyperparameters
45
  - false
46
  - - progress
47
+ - true
48
  - - pruner
49
  - median
50
  - - sampler
51
  - tpe
52
  - - save_freq
53
+ - 50000
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3865511864
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 200000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 500000.0
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:de4dcb325f47f58331444b8d2cd785a22641a598e2ad053139fa7d0a1f9a7ea2
3
- size 27219553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc3ddd65664719984950e4672fe466e160be906124d6862ed65afd70d7eb51da
3
+ size 27220129
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:d2f9820ae465bfc857183eeefd709176ebc8550d1f1e364376bcffb7deb4b218
3
- size 13505852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70287cde46d7e09436da7c39b8b390e2066792591ff89448c56fc323c11e4dbe
3
+ size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b32c857663cf231454836f9cff493e248c48ad829a4db67ba2d0721125408cd8
3
- size 13505178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bc7bf4f2e9145c63560e0de869ef0e4a54ea9cc76a959bd01da28f70de12dac
3
+ size 13505370
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,7 +2,7 @@
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.2.1
4
  - PyTorch: 2.1.0+cu121
5
- - GPU Enabled: False
6
  - Numpy: 1.23.5
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
 
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.2.1
4
  - PyTorch: 2.1.0+cu121
5
+ - GPU Enabled: True
6
  - Numpy: 1.23.5
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21cc3e94e4c280d432e1d1b5f0517c51eb8d542ce8bdfb78b9a5e7767fa05efb
3
- size 245204
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e04a9e34e6e3a9777c8635d651f38f0df320aa4f2e1764f44cdfabfd0a6a847f
3
+ size 265477
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 297.0, "std_reward": 156.99044556914922, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-27T05:06:40.876509"}
 
1
+ {"mean_reward": 239.0, "std_reward": 181.65626881558478, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-27T10:27:20.154271"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:714236c365d4100f39d46db6ad40a1e23237bc7631572d3a1922360b358b55f6
3
- size 9949
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635a724501f10027034d0ec279afb11f2a769eb4d36a4e1bca6244bc06dcb9e6
3
+ size 21846