Initial commit
Browse files- README.md +2 -2
- args.yml +1 -1
- 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
|
@@ -60,7 +60,7 @@ OrderedDict([('batch_size', 32),
|
|
60 |
('gradient_steps', 1),
|
61 |
('learning_rate', 0.0001),
|
62 |
('learning_starts', 100000),
|
63 |
-
('n_timesteps',
|
64 |
('optimize_memory_usage', True),
|
65 |
('policy', 'CnnPolicy'),
|
66 |
('target_update_interval', 1000),
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: 574.50 +/- 152.01
|
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', 1000000.0),
|
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 |
-
-
|
54 |
- - storage
|
55 |
- null
|
56 |
- - study_name
|
|
|
50 |
- - save_replay_buffer
|
51 |
- false
|
52 |
- - seed
|
53 |
+
- 2137647512
|
54 |
- - storage
|
55 |
- null
|
56 |
- - study_name
|
config.yml
CHANGED
@@ -18,7 +18,7 @@
|
|
18 |
- - learning_starts
|
19 |
- 100000
|
20 |
- - n_timesteps
|
21 |
-
-
|
22 |
- - optimize_memory_usage
|
23 |
- true
|
24 |
- - policy
|
|
|
18 |
- - learning_starts
|
19 |
- 100000
|
20 |
- - n_timesteps
|
21 |
+
- 1000000.0
|
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:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd012282ff6f645cb86b4f5ce06fdd6d13f8ba8decba69c22d7dffbbd8702be4
|
3 |
+
size 27222203
|
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:f871467ec6af02a2874be6354522b984c6c560d1220046c3cc8688a76ece9e1c
|
3 |
+
size 13503145
|
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 sha256:65658703485d0873b0e4bbe75c371816756b8612731dc003ea969285126a366a
|
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 sha256:4e3d8200894da682a408c41a1149f3373e50f1fe3d74b064b991159b05110cd5
|
3 |
+
size 193013
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 574.5, "std_reward": 152.01069041353637, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-30T13:15:37.666681"}
|
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 sha256:90b9bfb67c28493fc0e9c17b64187000b9e9538d10be38e280397ffa78178889
|
3 |
+
size 36445
|