Theoretically Guaranteed Policy Improvement Distilled from Model-Based Planning.
Chuming LiRuonan JiaJie LiuYinmin ZhangYazhe NiuYaodong YangYu LiuWanli OuyangPublished in: ECAI (2023)
Keyphrases
- action selection
- planning problems
- heuristic search
- optimal policy
- decision support
- ai planning
- partially observable
- reinforcement learning problems
- stochastic domains
- planning process
- significant improvement
- information technology
- production planning
- allocation policy
- markov decision problems
- goal oriented
- motion planning
- model free
- data sets
- domain specific
- case study
- artificial intelligence
- genetic algorithm
- neural network