mguevarra commited on
Commit
436c95a
1 Parent(s): 0528579

Initial commit

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: PongNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: -20.90 +/- 0.30
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: PongNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: -20.10 +/- 0.70
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 200000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 521415398
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3450138888
58
  - - storage
59
  - null
60
  - - 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
+ - 200000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-PongNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8de9120dd43c9e57a11d9c06264d4ce9c6dd0fc9d96a9a36b2fa4a826b96234
3
- size 13715472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c6c2f7dfd185ca1fd83e6391fcebfa6592d02d07909ced49b4a470ab6bd0d5b
3
+ size 27220208
dqn-PongNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-PongNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3fc84919e676e2bdcaa04814c7dfa2b7625d8d53a818418c6db25771364db93
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0117ab105330d3b53521b8cb5e1c5fdc7c008c873d670d9f6439c1ff2c08c5c
3
+ size 13505852
dqn-PongNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5e498a6abdc9c948e8239047236038b220f9f2794f06d87256763aa86a229c8
3
  size 13505178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd55ae1f4d502aee738baf1fb3387cc86af1f215dfdce96aa80f949bc464037f
3
  size 13505178
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:146a620a41af660eadaf0655eb5e73fcaeacc74ff24e28d4c2feb5c7a7c93960
3
- size 49516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9c4b79b348230e7334c0b473a6ad0db1c321115f9153a380f7271bed5800cfd
3
+ size 61524
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -20.9, "std_reward": 0.3, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-16T06:24:13.723630"}
 
1
+ {"mean_reward": -20.1, "std_reward": 0.7000000000000001, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-16T07:52:49.101329"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3579a7a38e36c36565ddfda36c38f701c1747153ea69617bdd615ae33caeed17
3
- size 3863
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03adda8487337bb1d9d1e2ac4d255f2139ed128e1d53f6dbc2d79009f08a3d14
3
+ size 7013