Hugging Face's logo

micheljperez
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files
xet
Community
micheljperez commited on
Commit
e1e61d2
·
1 Parent(s): 5f5f6a0

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 +5 -5
  9. replay.mp4 +2 -2
  10. results.json +1 -1
  11. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -10,7 +10,7 @@ model-index:
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
- value: 634.00 +/- 192.75
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
@@ -60,7 +60,7 @@ OrderedDict([('batch_size', 32),
60
  ('gradient_steps', 1),
61
  ('learning_rate', 0.0001),
62
  ('learning_starts', 100000),
63
- ('n_timesteps', 1000000),
64
  ('optimize_memory_usage', True),
65
  ('policy', 'CnnPolicy'),
66
  ('target_update_interval', 1000),
 
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
+ value: 1092.00 +/- 250.80
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
 
60
  ('gradient_steps', 1),
61
  ('learning_rate', 0.0001),
62
  ('learning_starts', 100000),
63
+ ('n_timesteps', 10000000),
64
  ('optimize_memory_usage', True),
65
  ('policy', 'CnnPolicy'),
66
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -50,7 +50,7 @@
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
- - 1227445971
54
  - - storage
55
  - null
56
  - - study_name
 
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
+ - 1081596659
54
  - - storage
55
  - null
56
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000
22
  - - optimize_memory_usage
23
  - true
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 10000000
22
  - - optimize_memory_usage
23
  - true
24
  - - policy
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f699a259bdcae19be7ac49fb378d255bfbce0596b30262292be5a5e5268dc5c
3
- size 27222203
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b58f0fe62a774daf2bfc9056f10e826452c33de333d1626bc68b3a1a8c4e988
3
+ size 27221974
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:cf9dfe791fe945cc9871033ce3c1ec7220ef924f2e1beb95e03ba78f0c63326b
3
- size 13503145
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f11405df4f68a2f5874d6a8a7a9f04b933c524697ad0eea7c8f4dcf326ce809
3
+ size 13502953
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a18f8a70ae9b18e8c469169ec3a1e2f460903fd5f9ce45a60791e4512883027d
3
- size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78a1c123023c53acec1377469a02906be02824736fc9a39d82c206fb399518f4
3
+ size 13504745
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,7 +1,7 @@
1
- OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
2
- Python: 3.7.13
3
  Stable-Baselines3: 1.5.1a8
4
- PyTorch: 1.11.0+cu113
5
- GPU Enabled: True
6
- Numpy: 1.21.6
7
  Gym: 0.21.0
 
1
+ OS: macOS-12.4-arm64-arm-64bit Darwin Kernel Version 21.5.0: Tue Apr 26 21:08:37 PDT 2022; root:xnu-8020.121.3~4/RELEASE_ARM64_T6000
2
+ Python: 3.8.9
3
  Stable-Baselines3: 1.5.1a8
4
+ PyTorch: 1.11.0
5
+ GPU Enabled: False
6
+ Numpy: 1.23.0
7
  Gym: 0.21.0
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a34aa8409ff5ab08be682e50e71aa44416a31bf767bc66a92c4e8429fc423e7
3
- size 224415
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5b7e4ff1636b10883c5c8441fcefb17054a845adef1b8849259a53ce235ac89
3
+ size 192717
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 634.0, "std_reward": 192.753728887407, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-22T19:17:23.582195"}
 
1
+ {"mean_reward": 1092.0, "std_reward": 250.80071770232237, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-24T13:36:46.660541"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61593abe3315820dce289e6484f7f8b1abbbd4c56a43c68f375d764c8eb3709d
3
- size 38054
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41192368ba217cdbe01e363bd9bb0668f57d888741b6846f793e8eeb5ab68e58
3
+ size 272785