RalphX1 commited on
Commit
fa1fa8d
1 Parent(s): 7c388b6

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', 30000.0),
64
  ('optimize_memory_usage', True),
65
  ('policy', 'CnnPolicy'),
66
  ('target_update_interval', 1000),
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
+ value: 6.50 +/- 16.29
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', 100000.0),
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
- - 1391799702
54
  - - storage
55
  - null
56
  - - study_name
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
+ - 1512559051
54
  - - storage
55
  - null
56
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 30000.0
22
  - - optimize_memory_usage
23
  - true
24
  - - policy
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 100000.0
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:b9f7a08ec5f99f47e6a0adb118ba19d534ed98c264395b305a2e2ee4494fbc0f
3
- size 13717618
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aea2dc17ce2ac282fab393e13a39d62184acf58e6b2b13ae20636c67854ee88f
3
+ size 13719481
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dd61c399b2a67a2a37f26500398a1c0b151f3f18d11ec46b7626d73201b5ac0
3
  size 13504745
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28776c5248792a117440d990424fc5ab4390fe2f3e8d46457feaa5c34a7c28a4
3
  size 13504745
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25fcb8f4cd387bbd8ea8f1869dda23f9bc38859fa045e4ba505c96295aab752b
3
- size 275554
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec26970276c80c00636ff43ee53dfe8e2e18fb4695a48055e8a79c88e18cdca
3
+ size 256433
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 14.5, "std_reward": 12.338962679253067, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-10T13:22:58.457078"}
1
+ {"mean_reward": 6.5, "std_reward": 16.28649747490233, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-10T13:40:14.656633"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40d1c8c08767c25d68bc5a93d80ea117199076e72646b750ed60e4badf1a00a7
3
- size 2352
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ed68b4f6c7c04c25904a39ee6120c66e05125da030dc2817fb005ababbec87b
3
+ size 5681