Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning.
Jinxin LiuDonglin WangQiangxing TianZhengyu ChenPublished in: AAAI (2022)
Keyphrases
- reinforcement learning
- agent learns
- intrinsic motivation
- optimal policy
- function approximators
- reward signal
- function approximation
- learning agent
- reinforcement learning algorithms
- college students
- markov decision processes
- state space
- agent receives
- reward function
- statistically significant
- pilot study
- intelligent tutoring systems
- cognitive style
- learning process
- multi agent
- web services
- information systems
- learning algorithm