bkaemper commited on
Commit
a4302ba
1 Parent(s): 291d9bf

Initial commit

Browse files
README.md CHANGED
@@ -10,7 +10,7 @@ model-index:
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
- value: 14.50 +/- 12.34
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', False),
65
  ('policy', 'CnnPolicy'),
66
  ('target_update_interval', 1000),
 
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
+ value: 774.50 +/- 288.79
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', 1000000.0),
64
  ('optimize_memory_usage', False),
65
  ('policy', 'CnnPolicy'),
66
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -50,7 +50,7 @@
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
- - 1512810446
54
  - - storage
55
  - null
56
  - - study_name
 
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
+ - 89745579
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
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 1000000.0
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 sha256:9a35acaef3aa1a5956e39aabe673ad021ca1c295889846b1623ae5f5077f8d6a
3
- size 13719804
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf59808bdd8277a0ae593a7cb770deaa781775b013e88a6cdd41e7f6020626e7
3
+ size 27224866
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 sha256:71a21ae67866ddb856ecbb70c8ba0e04af200cc5da53fbcb90e773d87e996b31
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:042cdf3a73c7d1e0df18f43e0c18f21ba0dc80e3c7033a0f2ee9119f03287860
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:f1abb428bcdbac6b68c8bd81fa3fea099d554c5235a3ce46c539d8203887449a
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:568e81575769d0d58dd6a0c8ddbad8472bcb982367681cb8ec6f60b37af71c87
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77a34c0bfe681d4556bdbe379a0b364bd442fd416394947a43e96dd7375a1c05
3
- size 275951
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ddacec5f1859e6cc6560387c104e8dd90d69ea4c7b0d61b2da66e4f2515f74
3
+ size 185366
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 14.5, "std_reward": 12.338962679253067, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-07-29T08:44:22.055295"}
 
1
+ {"mean_reward": 774.5, "std_reward": 288.78582028901627, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-07-29T10:22:56.446728"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d711ddd1bea4ded28248b530e65b208bc4dec412c3ee397ee0abc861c26370e
3
- size 5604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9317b52290676f6a252c442855e892d502dbfd24dda81949b0d1714976ca0aa5
3
+ size 36694