Online Planning for Interactive-POMDPs using Nested Monte Carlo Tree Search.
Jonathon SchwartzRuijia ZhouHanna KurniawatiPublished in: IROS (2022)
Keyphrases
- monte carlo tree search
- monte carlo search
- bayesian reinforcement learning
- monte carlo
- partially observable markov decision processes
- evaluation function
- partially observable
- mixed initiative
- planning problems
- predictive state representations
- finite state
- belief state
- optimal policy
- markov decision processes
- temporal difference
- reinforcement learning
- point based value iteration
- fixed point
- decision problems
- dynamical systems
- learning experience
- lower bound