Planning and Reinforcement Learning for General-Purpose Service Robots.
Yuqian JiangPublished in: IJCAI (2021)
Keyphrases
- general purpose
- service robots
- reinforcement learning
- special purpose
- action selection
- function approximation
- human robot interaction
- application specific
- home environment
- macro actions
- heuristic search
- domain specific
- state space
- reinforcement learning algorithms
- planning problems
- complex domains
- domain independent
- model free
- manipulation tasks
- blocks world
- planning process
- programming language
- learning algorithm
- stochastic domains
- multi agent
- partially observable
- ai planning
- markov decision process
- temporal difference
- motion planning
- optimal control