gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 11:10:20 +01:00
Code Issues Projects Releases Wiki Activity

Updating PPO references per issue #11

Browse Source
This commit is contained in:
Gal Leibovich
2017-10-24 16:57:44 +03:00
parent 43bc359166
commit eb0b57d7fa
3 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
agents/ppo_agent.py
View File

@@ -19,7 +19,7 @@ from random import shuffle
import tensorflow as tf
# Proximal Policy Optimization - https://arxiv.org/pdf/1707.02286.pdf
# Proximal Policy Optimization - https://arxiv.org/pdf/1707.06347.pdf
class PPOAgent(ActorCriticAgent):
def __init__(self, env, tuning_parameters, replicated_device=None, thread_id=0):
ActorCriticAgent.__init__(self, env, tuning_parameters, replicated_device, thread_id,