Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning.
Jinxin LiuDonglin WangQiangxing TianZhengyu ChenPublished in: CoRR (2021)
Keyphrases
- agent learns
- reinforcement learning
- intrinsic motivation
- reward signal
- optimal policy
- function approximators
- statistically significant
- learning agent
- function approximation
- college students
- state space
- markov decision processes
- agent receives
- reinforcement learning algorithms
- learning algorithm
- job satisfaction
- learning process
- reward function
- learning experience