Hugging Face's logo

klashenrik
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
klashenrik commited on
Commit
738c212
•
1 Parent(s): 36bfe6c

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 +1 -1
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +4 -4
  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: 550.00 +/- 108.17
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: 991.00 +/- 342.79
20
  name: mean_reward
21
  verified: false
22
  ---
 
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
+ ('n_timesteps', 10000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3144365924
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1364573656
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
+ - 10000000.0
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 sha256:90b7d17c36ab212d8a2e99ce461e9835067d06f781dd045a89ef67e910a61ce0
3
- size 27224788
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:389fcaf3c1d003061bf2422e2b71784bb22c32a5af34283221315ee93eaada95
3
+ size 27225388
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:ef70cf028a6ceeab0a862942c02632a234520efcdb22438c489b1ce9275a5189
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:893fe65eb5fd148db6e9446f8a59d8edb8ca3c578ac77221b7e47ebba74733d8
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f3f87cbf68feb906c153c28fdac85eb732b3bfc4bbca862b1f79599ee680ec0
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b06a3b6216a583977f2a7ee4f53a601d6107e0a16dbbb2ad0ca9eecec98e19d
3
  size 13504937
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,7 +1,7 @@
1
- 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
 
1
+ OS: Linux-5.15.80-gentoo-dist-x86_64-AMD_Ryzen_7_5800X_8-Core_Processor-with-glibc2.36 #1 SMP Sat Nov 26 13:36:10 -00 2022
2
+ Python: 3.10.9
3
  Stable-Baselines3: 1.6.2
4
+ PyTorch: 1.13.1+cu117
5
  GPU Enabled: True
6
+ Numpy: 1.24.0
7
  Gym: 0.21.0
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb63b1b9ef1ebd2c07cb0d8f83099d00c25c648b1b4b07e3aabc88432d27942d
3
- size 185888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a757c83b724011559ccb908e09014f0627679ae87dcc0d76820e1d1bf1ce24dd
3
+ size 221125
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 550.0, "std_reward": 108.16653826391968, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-20T11:34:38.445700"}
 
1
+ {"mean_reward": 991.0, "std_reward": 342.7885645700568, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-21T09:25:30.468313"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66ed4fd35d765d9c456967440b2786c423e5e1b54f2ff6cc22251541609f13b0
3
- size 38623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1219cc0bba6400df73d7ed699800a9d09828fafb1034376ac38131dcfe2185a
3
+ size 267091