PranavHonrao commited on
Commit
7793378
1 Parent(s): c01503b

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: 195.50 +/- 60.31
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),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 541.50 +/- 211.99
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 1000000),
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
- - 874396990
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 557523403
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 1000000
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 sha256:789fe6e5b2f120d5a2416f12641474b83872168c1faa88b35ee05a3697dbc460
3
- size 13715007
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e2621685d8dc22e259028139f296d6d1dd7dfab163d9146d26847ef2a16b712
3
+ size 27220132
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:e3fc84919e676e2bdcaa04814c7dfa2b7625d8d53a818418c6db25771364db93
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4599ea92da47e6858574dd44f9e970f65acce236b0ec0710b06a4093510f49f
3
+ size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec85409a548025e6cff30b49561535f7e9b7bc8b1ca99625d527133c54fd599a
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56a2065ae7a05f588470f32d134135281e9a9fa96e14209a5fac717d0d41ebeb
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:217f5593f29dd80edc54711c4b90458824047b290b28348c6289a2d3aed9d7bc
3
- size 247480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0126841009d863560c20938414d02c83b9c397c7be4f38dd747fb6db195bb782
3
+ size 207211
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 195.5, "std_reward": 60.309617806781034, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-26T22:38:50.822629"}
 
1
+ {"mean_reward": 541.5, "std_reward": 211.991155475883, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-27T00:51:10.831941"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:937909cb45a74df6ffc00820a27e7c9622b793eb337e89272ccdd2dce0485f70
3
- size 6026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:629e73dc2540b4f419e7b420eebc816fdb4d0e471675b1d6d34233bc723c8cc3
3
+ size 37572