debisoft commited on
Commit
8831d20
·
verified ·
1 Parent(s): 3ca59aa

Initial commit

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 263.50 +/- 141.55
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -71,7 +71,7 @@ OrderedDict([('batch_size', 32),
71
  ('exploration_fraction', 0.1),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
- ('learning_rate', 1e-05),
75
  ('learning_starts', 100000),
76
  ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 257.00 +/- 38.81
20
  name: mean_reward
21
  verified: false
22
  ---
 
71
  ('exploration_fraction', 0.1),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
+ ('learning_rate', 0.001),
75
  ('learning_starts', 100000),
76
  ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 2719719223
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 940535275
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 1.0e-05
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23abe03056c37d7a85f27aec66bb69f50dffbc66dd2c2551d5edfddb334af517
3
  size 27219627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1b1dcfbc455f4902e743a4a1e03571eee05216d3ce440335b6b65617ea847fc
3
  size 27219627
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 sha256:163378d0479fe846bbea75af5e16c3a6284a471e89573882ec152238a2ee0f95
3
  size 13506569
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88487bb4b0f0adbaa87f6411145589e734aeb1893b12ef2c70cbfad65b66a234
3
  size 13506569
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cedc968ac18e4fc1d1b1c2b9ddcb6abc0bcce7c440fd2fefd6d5a9e3bd6a8df
3
  size 13505767
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ac572c79e435bf8f18e227d50afc006f89e7e8ad2b9d870ecef887f98dba1cc
3
  size 13505767
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb3b9257439e10c6943122585960fca8eb4859b77abc983f692979c0ff984fa4
3
- size 254190
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea07c01915a2caa59cdb3e4728efe266b1af65268e459ecbbb534c14d29b3bc
3
+ size 246606
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 263.5, "std_reward": 141.54592894181027, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-23T03:38:52.287127"}
 
1
+ {"mean_reward": 257.0, "std_reward": 38.80721582386451, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-23T04:28:28.565545"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e9d3b63072ab00eb3e9b41271a7421ed17a24e6f8e6f873c88b109757a7dd87
3
- size 42305
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd5eef239a4aceb190d1f245b0534f0abfe55010f742dee39e27aff33f6ed557
3
+ size 40014