devetle commited on
Commit
b3345b8
1 Parent(s): 0018d62

Initial commit

Browse files
README.md CHANGED
@@ -10,7 +10,7 @@ model-index:
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
- value: 528.00 +/- 153.97
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: 622.00 +/- 131.55
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', 1800000.0),
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
- - 3763560085
54
  - - storage
55
  - null
56
  - - study_name
 
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
+ - 2137192785
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
+ - 1800000.0
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 sha256:5a58a7d965b96dbb4f59e0b4a0b1cd132f37f133926385cb751429312abe380a
3
  size 27222203
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b37712db2c9e8a0a20cca82f3646438630e2ae8957a11e198567f5721433a586
3
  size 27222203
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 sha256:59f7c5b7fbca5f34862a83bda2f7e49f8ee3f5401d02c69bd4a0a04755708dcc
3
  size 13503145
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:123ba4602ef910988c76f9149c7c696d62be518752adecc70cb610c6a9ba3883
3
  size 13503145
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e340e00f83818595cf80d013453870e9b22d88be6ef11f4ce81a4eb40a5f82d5
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:440ff9ceaf4177b3111b0803d99a2278a8c53a13027105f0ce2c96b4c5f0cf93
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfb5c2d72dd4b5929c5115d9959a06a4643fe0269b948a335a35e5dc6c4d7173
3
- size 236721
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1be24309b15f27f4adccee5a4a3247479023566804eb1539a5588464b1550da
3
+ size 207487
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 528.0, "std_reward": 153.9675290442761, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-19T03:35:01.883139"}
 
1
+ {"mean_reward": 622.0, "std_reward": 131.55227098001768, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-19T09:28:50.873016"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e8c4c5d1f62243f67eb1d8b812f27b27a11f30efbc4e76a29c3a6785f572e24
3
- size 36060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aafa5b2dde9a61a193030dcb6c663dd1276e6eea077415e912cbd21d470c071e
3
+ size 58497