Initial commit
Browse files- README.md +2 -2
- args.yml +2 -2
- config.yml +1 -1
- dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
- dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
- dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
- dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
- train_eval_metrics.zip +2 -2
README.md
CHANGED
@@ -10,7 +10,7 @@ model-index:
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
-
value:
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
@@ -67,7 +67,7 @@ OrderedDict([('batch_size', 32),
|
|
67 |
('gradient_steps', 1),
|
68 |
('learning_rate', 0.0001),
|
69 |
('learning_starts', 200000),
|
70 |
-
('n_timesteps',
|
71 |
('normalize', False),
|
72 |
('optimize_memory_usage', True),
|
73 |
('policy', 'CnnPolicy'),
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: 1295.00 +/- 492.10
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
|
|
67 |
('gradient_steps', 1),
|
68 |
('learning_rate', 0.0001),
|
69 |
('learning_starts', 200000),
|
70 |
+
('n_timesteps', 10000000.0),
|
71 |
('normalize', False),
|
72 |
('optimize_memory_usage', True),
|
73 |
('policy', 'CnnPolicy'),
|
args.yml
CHANGED
@@ -54,7 +54,7 @@
|
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
-
-
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
@@ -72,7 +72,7 @@
|
|
72 |
- - vec_env
|
73 |
- dummy
|
74 |
- - verbose
|
75 |
-
-
|
76 |
- - wandb_entity
|
77 |
- null
|
78 |
- - wandb_project_name
|
|
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
+
- 4248638377
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
|
|
72 |
- - vec_env
|
73 |
- dummy
|
74 |
- - verbose
|
75 |
+
- 0
|
76 |
- - wandb_entity
|
77 |
- null
|
78 |
- - wandb_project_name
|
config.yml
CHANGED
@@ -20,7 +20,7 @@
|
|
20 |
- - learning_starts
|
21 |
- 200000
|
22 |
- - n_timesteps
|
23 |
-
-
|
24 |
- - normalize
|
25 |
- false
|
26 |
- - optimize_memory_usage
|
|
|
20 |
- - learning_starts
|
21 |
- 200000
|
22 |
- - n_timesteps
|
23 |
+
- 10000000.0
|
24 |
- - normalize
|
25 |
- false
|
26 |
- - optimize_memory_usage
|
dqn-SpaceInvadersNoFrameskip-v4.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63887a1cfa7666a5cf42743f4cba5d9fdfd2da44ae24f6fb9432092181f4375f
|
3 |
+
size 27224849
|
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:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a64f47f91aa7ef294ea9ee161cdf2e8c67d80097e82c641fca071e1a17b3a4e5
|
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:
|
3 |
size 13504937
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36d3d1285b924bff6033612a1a92582abb1cfd807e0753354adef231b2f6fecb
|
3 |
size 13504937
|
replay.mp4
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df9c9e1c9de793c32ac1c59c0f58ad73a354123bfcb7594df3f915c26d8e85c8
|
3 |
+
size 192587
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 1295.0, "std_reward": 492.09755130461684, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-24T11:58:59.694203"}
|
train_eval_metrics.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a57e6ac55818215f2397713973650272eff28049f8147e859419e0415dc11ce9
|
3 |
+
size 272504
|