Yanka Ribeiro
commited on
Commit
·
0e8a007
1
Parent(s):
661c4a0
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
|
@@ -16,7 +16,7 @@ model-index:
|
|
| 16 |
type: SpaceInvadersNoFrameskip-v4
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
-
value:
|
| 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',
|
| 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: 312.50 +/- 34.51
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
|
|
|
| 72 |
('gradient_steps', 1),
|
| 73 |
('learning_rate', 0.0001),
|
| 74 |
('learning_starts', 100000),
|
| 75 |
+
('n_timesteps', 1000000.0),
|
| 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 |
-
-
|
| 58 |
- - storage
|
| 59 |
- null
|
| 60 |
- - study_name
|
|
|
|
| 54 |
- - save_replay_buffer
|
| 55 |
- false
|
| 56 |
- - seed
|
| 57 |
+
- 1384301237
|
| 58 |
- - storage
|
| 59 |
- null
|
| 60 |
- - study_name
|
config.yml
CHANGED
|
@@ -18,7 +18,7 @@
|
|
| 18 |
- - learning_starts
|
| 19 |
- 100000
|
| 20 |
- - n_timesteps
|
| 21 |
-
-
|
| 22 |
- - optimize_memory_usage
|
| 23 |
- false
|
| 24 |
- - policy
|
|
|
|
| 18 |
- - learning_starts
|
| 19 |
- 100000
|
| 20 |
- - n_timesteps
|
| 21 |
+
- 1000000.0
|
| 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:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fea6abde2dc897db41961ec38496e74a08a79ca457b29a45e5cd4bfdc7062d3c
|
| 3 |
+
size 27218508
|
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:c3ebfca242bb2d024034816f07716d33665ee3bb3ac14c14292d2c6068ca7e7e
|
| 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 sha256:45530e9605893df7d85e0be378f5621911a3c39bc71490940a8b57566d24a286
|
| 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 sha256:5032e90c3aecb8d493a37f4c8a0345cb6dc89477c0638eee493c674881808684
|
| 3 |
+
size 287216
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward":
|
|
|
|
| 1 |
+
{"mean_reward": 312.5, "std_reward": 34.514489710844636, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-10-19T13:47:28.662763"}
|
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:ecdf49f73e8932c1b168e2956e04718acd27d5ac88deb3bbc9d235f814cc193c
|
| 3 |
+
size 24014
|