Integrating Planning and Deep Reinforcement Learning via Automatic Induction of Task Substructures.
Jung-Chun LiuChi-Hsien ChangShao-Hua SunTian-Li YuPublished in: ICLR (2024)
Keyphrases
- reinforcement learning
- machine learning
- partially observable
- action selection
- complex domains
- fully automatic
- stochastic domains
- partial observability
- blocks world
- function approximation
- planning problems
- markov decision processes
- heuristic search
- decision support
- dynamic programming
- data structure
- multi agent
- dynamical systems
- motion planning
- semi automatic
- temporal difference
- state space
- planning systems
- action space