Hierarchical Reinforcement Learning from Demonstration via Reachability-Based Reward Shaping.
Xiaozhu GaoJinhui LiuBo WanLingling AnPublished in: Neural Process. Lett. (2024)
Keyphrases
- reward shaping
- reinforcement learning
- state space
- complex domains
- reinforcement learning algorithms
- markov decision problems
- markov chain
- dynamic programming
- neural network
- markov decision processes
- function approximation
- action selection
- reward function
- training data
- knowledge base
- learning algorithm
- machine learning