ledmands
commited on
Commit
•
b00577c
1
Parent(s):
a01bf38
Updated README
Browse files
README.md
CHANGED
|
@@ -6,6 +6,8 @@ tags:
|
|
| 6 |
- Reinforcement Learning
|
| 7 |
- Atari
|
| 8 |
- Pac-Man
|
|
|
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: DQN
|
| 11 |
results:
|
|
@@ -20,6 +22,8 @@ model-index:
|
|
| 20 |
value: none
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
|
|
|
|
|
|
| 23 |
---
|
| 24 |
|
| 25 |
# Agent using DQN to play ALE/Pacman-v5
|
|
|
|
| 6 |
- Reinforcement Learning
|
| 7 |
- Atari
|
| 8 |
- Pac-Man
|
| 9 |
+
pipeline_tag: reinforcement-learning
|
| 10 |
+
|
| 11 |
model-index:
|
| 12 |
- name: DQN
|
| 13 |
results:
|
|
|
|
| 22 |
value: none
|
| 23 |
name: mean_reward
|
| 24 |
verified: false
|
| 25 |
+
output:
|
| 26 |
+
url: videos/dqn_v2-8_bestmodel-10000steps.mp4
|
| 27 |
---
|
| 28 |
|
| 29 |
# Agent using DQN to play ALE/Pacman-v5
|