Initial commit
Browse files- README.md +3 -3
- args.yml +1 -1
- config.yml +2 -2
- dqn-PongNoFrameskip-v4.zip +2 -2
- dqn-PongNoFrameskip-v4/data +0 -0
- dqn-PongNoFrameskip-v4/policy.optimizer.pth +2 -2
- dqn-PongNoFrameskip-v4/policy.pth +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
- train_eval_metrics.zip +2 -2
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: PongNoFrameskip-v4
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value: -
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
@@ -70,8 +70,8 @@ OrderedDict([('batch_size', 32),
|
|
70 |
('exploration_fraction', 0.1),
|
71 |
('frame_stack', 4),
|
72 |
('gradient_steps', 1),
|
73 |
-
('learning_rate', 0.
|
74 |
-
('learning_starts',
|
75 |
('n_timesteps', 100000.0),
|
76 |
('optimize_memory_usage', False),
|
77 |
('policy', 'CnnPolicy'),
|
|
|
16 |
type: PongNoFrameskip-v4
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: -20.90 +/- 0.30
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
70 |
('exploration_fraction', 0.1),
|
71 |
('frame_stack', 4),
|
72 |
('gradient_steps', 1),
|
73 |
+
('learning_rate', 0.001),
|
74 |
+
('learning_starts', 100000),
|
75 |
('n_timesteps', 100000.0),
|
76 |
('optimize_memory_usage', False),
|
77 |
('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
|
|
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
+
- 1309108614
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
config.yml
CHANGED
@@ -14,9 +14,9 @@
|
|
14 |
- - gradient_steps
|
15 |
- 1
|
16 |
- - learning_rate
|
17 |
-
- 0.
|
18 |
- - learning_starts
|
19 |
-
-
|
20 |
- - n_timesteps
|
21 |
- 100000.0
|
22 |
- - optimize_memory_usage
|
|
|
14 |
- - gradient_steps
|
15 |
- 1
|
16 |
- - learning_rate
|
17 |
+
- 0.001
|
18 |
- - learning_starts
|
19 |
+
- 100000
|
20 |
- - n_timesteps
|
21 |
- 100000.0
|
22 |
- - optimize_memory_usage
|
dqn-PongNoFrameskip-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:a346841583bd867c8e0327b5ce35f644c200c29cc27d55035cc06fa96137d762
|
3 |
+
size 13713330
|
dqn-PongNoFrameskip-v4/data
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
dqn-PongNoFrameskip-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 sha256:0deb940c86ab5538de5b7bd48f2a3305a3491099536c85fbff2bf1588b36f07a
|
3 |
+
size 687
|
dqn-PongNoFrameskip-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 sha256:7cc2dd84acc1d6ddb5ea08da65e0c2d6480518d83fbd3f1c021218d06d93b900
|
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:c4153e78cf36a7ed336ccdd10c8863eb56aff74784e4e1195f9ead3b2470bdc2
|
3 |
+
size 49492
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": -
|
|
|
1 |
+
{"mean_reward": -20.9, "std_reward": 0.3, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-06-20T08:58:52.810733"}
|
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 sha256:656153711e052596f8d0c9af2219683f73fd9411322fef0835d56f8b16564d98
|
3 |
+
size 3836
|