A New View on Planning in Online Reinforcement Learning.
Kevin RoiceParham Mohammad PanahiScott M. JordanAdam WhiteMartha WhitePublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- online learning
- partially observable
- state space
- action selection
- real time
- reinforcement learning algorithms
- travel planning
- dynamic programming
- deterministic domains
- ai planning
- function approximation
- planning problems
- macro actions
- planning process
- classical planning
- control policy
- blocks world
- decision theoretic
- model free
- planning domains
- evaluation function
- heuristic search
- decision support
- supervised learning
- learning process
- data sets