Hugging Face's logo

danieladejumo
/
dqn-QbertNoFrameskip-v4

Reinforcement Learning
stable-baselines3
QbertNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
danieladejumo commited on
Commit
6d079c5
·
1 Parent(s): a16e56e

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-QbertNoFrameskip-v4.zip +2 -2
  5. dqn-QbertNoFrameskip-v4/data +0 -0
  6. dqn-QbertNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. dqn-QbertNoFrameskip-v4/policy.pth +1 -1
  8. dqn-QbertNoFrameskip-v4/system_info.txt +3 -3
  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: 1057.50 +/- 1063.49
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', 1000000.0),
64
  ('optimize_memory_usage', True),
65
  ('policy', 'CnnPolicy'),
66
  ('target_update_interval', 1000),
 
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
+ value: 3342.50 +/- 1668.76
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', 2500000.0),
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
- - 4151685021
54
  - - storage
55
  - null
56
  - - study_name
 
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
+ - 3526269835
54
  - - storage
55
  - null
56
  - - 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
  - true
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 2500000.0
22
  - - optimize_memory_usage
23
  - true
24
  - - policy
dqn-QbertNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b9915ce4ef35ae3d50876844c95f99fe9c9cb1bb2e1018d41481fc21ef8285b
3
- size 27222202
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe74369bffddb37b4682dea0cbce616b66898f4af0f30464b13c1d665bd85c6c
3
+ size 27222198
dqn-QbertNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-QbertNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d546f23dd9dd306abe44b6e5cadc181258780668c97e6276e808f7c0914da70
3
  size 13503145
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2e48b92d8e0183da0f13f3678fed0eb04945ab66bfad3caf467f5e441aa7bdf
3
  size 13503145
dqn-QbertNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a2bb39a704355727e1507d9394651db3274a14bd6882a74e44cff4982e64aec
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f18f4d5c85f610fb08ea83e9442221e536ff9165193d262cb90eb6dd5b200ee
3
  size 13504937
dqn-QbertNoFrameskip-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: Linux-5.10.123+-x86_64-with-debian-bullseye-sid #1 SMP Wed Jun 22 22:52:42 UTC 2022
2
+ Python: 3.7.12
3
  Stable-Baselines3: 1.5.1a8
4
+ PyTorch: 1.11.0
5
  GPU Enabled: True
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 sha256:4ff30afb855fe06ad1b4122c92002b7edac1bc9fc10f662b1b3a0565b261359f
3
- size 126227
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78b7b15d45303affcd9718bb60ec594e9881af69959be7f58cef52fe88cc4572
3
+ size 149490
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 1057.5, "std_reward": 1063.4877761403748, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-30T22:44:53.222415"}
 
1
+ {"mean_reward": 3342.5, "std_reward": 1668.758895107379, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-07-01T18:30:45.540529"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c703a11ab82acc59e1d66ac3bb88fd68bd60d83a014636e5035a5774b9ff9f5f
3
- size 46527
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f29ccb123e16f1354fd636b8e696bf14dcc62c70cd309a491aa0a4437e0cb48
3
+ size 101617