Hugging Face's logo

RalphX1
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
RalphX1 commited on
Commit
713a091
•
1 Parent(s): fa1fa8d

Initial commit

Browse files
Files changed (9) 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.pth +1 -1
  7. replay.mp4 +2 -2
  8. results.json +1 -1
  9. 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: 6.50 +/- 16.29
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', 100000.0),
64
  ('optimize_memory_usage', True),
65
  ('policy', 'CnnPolicy'),
66
  ('target_update_interval', 1000),
 
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
+ value: 374.00 +/- 214.89
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', 10000.0),
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
- - 1512559051
54
  - - storage
55
  - null
56
  - - study_name
 
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
+ - 1058099880
54
  - - storage
55
  - null
56
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - true
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 10000.0
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:aea2dc17ce2ac282fab393e13a39d62184acf58e6b2b13ae20636c67854ee88f
3
- size 13719481
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:028409d968eead7b776794343783826eccc2f0302c89e22f5acb4f30415c6dc8
3
+ size 13716129
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28776c5248792a117440d990424fc5ab4390fe2f3e8d46457feaa5c34a7c28a4
3
  size 13504745
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668f6a018a101813c8670aa277ebddb5e34dc08a9ef6cd1519ab9df1965d2a91
3
  size 13504745
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fec26970276c80c00636ff43ee53dfe8e2e18fb4695a48055e8a79c88e18cdca
3
- size 256433
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b231c3e33922a65189db4066e7414df0b5a66d5fa35017253dc63dd0d43b457
3
+ size 233415
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 6.5, "std_reward": 16.28649747490233, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-10T13:40:14.656633"}
 
1
+ {"mean_reward": 374.0, "std_reward": 214.89299662855464, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-10T13:56:55.359854"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ed68b4f6c7c04c25904a39ee6120c66e05125da030dc2817fb005ababbec87b
3
- size 5681
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4281aee5795bd9d454d40ffd97e1c069054b9ec27cb4fdb2d0a7647c5ebb3761
3
+ size 608