Itinerary Planning via Deep Reinforcement Learning.
Shengxin ChenBo-Hao ChenZhaojiong ChenYunBing WuPublished in: ICMR (2020)
Keyphrases
- reinforcement learning
- macro actions
- heuristic search
- action selection
- deterministic domains
- stochastic domains
- multi agent
- goal oriented
- model free
- function approximation
- state space
- temporal difference
- partially observable
- planning problems
- motion planning
- reward shaping
- ai planning
- decision support
- dynamic programming
- partially observable markov decision processes
- complex domains
- robotic control
- hidden markov models
- reinforcement learning problems
- temporal difference learning
- single agent
- domain independent
- path planning
- markov decision processes