Density-based Curriculum for Multi-goal Reinforcement Learning with Sparse Rewards.
Deyu YangHanbo ZhangXuguang LanJishiyu DingPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- markov decision processes
- reinforcement learning algorithms
- multi agent
- optimal policy
- function approximation
- state space
- hidden state
- sparse representation
- partially observable
- sparse data
- model free
- reward shaping
- learning algorithm
- density based clustering
- clustering algorithm
- agent learns
- learning goals
- dynamic programming
- markov decision process
- action space
- compressive sensing
- optimal control
- anomaly detection
- least squares