search

awjuliani / DeepRL-Agents

A set of Deep Reinforcement Learning Agents implemented in Tensorflow.
MIT License
2.24k stars 826 forks source link

Low Rewards for DRQN #38

Open yenlianglintw opened 7 years ago

yenlianglintw commented 7 years ago

I tried with DRQN code for both partial or full observability cases. However, I found it sometimes gets trapped into repeated actions and obtains very low rewards. Do you have the same problems before ? Thanks