Hugging Face's logo

numan966
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
numan966 commited on
Commit
fa3f6a4
•
1 Parent(s): 6086c46

Initial commit

Browse files
Files changed (12) 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/_stable_baselines3_version +1 -1
  6. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  8. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  9. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
  10. replay.mp4 +2 -2
  11. results.json +1 -1
  12. 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: 687.00 +/- 375.37
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -70,7 +70,7 @@ OrderedDict([('batch_size', 32),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
  ('n_timesteps', 3000000.0),
76
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 767.50 +/- 321.09
20
  name: mean_reward
21
  verified: false
22
  ---
 
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0002),
74
  ('learning_starts', 100000),
75
  ('n_timesteps', 3000000.0),
76
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 680832506
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1170954008
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0002
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9aae3951810e4666dca4f6bc72227bec9a3b1d359a1c3c80dd865033996c9ff
3
- size 27224803
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91970ee4ff0bf9de913d6fca855586c424e2e1b576299c29d17c275b79c8c1be
3
+ size 27224807
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 1.7.0
 
1
+ 1.8.0a2
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 sha256:19981498aa98a56e452dbb6fad6967dec796337930af42576f6a36b44499eb6b
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb46fe0dbad061c7bc218690aac840586910fc1dd7d78c8ccd4b958015f5bdfd
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2de920ab4c030cf67a341f318b115a79b4afac0b3c99c832615cae96facc77b7
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a04dcd3602e9a6f5d018ebdb1aadf009617e5ca8d6fc85e08e64a5d614ec6cd2
3
  size 13504937
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,6 +1,6 @@
1
  - OS: Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
2
  - Python: 3.8.10
3
- - Stable-Baselines3: 1.7.0
4
  - PyTorch: 1.13.1+cu116
5
  - GPU Enabled: True
6
  - Numpy: 1.21.6
 
1
  - OS: Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
2
  - Python: 3.8.10
3
+ - Stable-Baselines3: 1.8.0a2
4
  - PyTorch: 1.13.1+cu116
5
  - GPU Enabled: True
6
  - Numpy: 1.21.6
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a60328c440c5abdc328bee99be56cab84d65f043ad86089f9d7d8b1f41f7c0f0
3
- size 181723
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57eaaa2903f28044f1610f80427deb7122f9d2a19a8e438c65d2e21cedeec142
3
+ size 208157
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 687.0, "std_reward": 375.3678196116444, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-21T22:17:50.939825"}
 
1
+ {"mean_reward": 767.5, "std_reward": 321.08604765701045, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-31T16:03:24.464579"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95db4c04f94e896b1904250bfa04fe7e9abde3a6cd36791ee3bcd70cb5017b5f
3
- size 90218
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e758768e4895629de54985c77004b5f487dd3a9a6c4424260eecd30e9009b6d5
3
+ size 91429