State-Continuity Approximation of Markov Decision Processes via Finite Element Methods for Autonomous System Planning.
Junhong XuKai YinLantao LiuPublished in: IEEE Robotics Autom. Lett. (2020)
Keyphrases
- markov decision processes
- state space
- partially observable
- action space
- macro actions
- finite element methods
- decision theoretic planning
- planning under uncertainty
- optimal policy
- planning problems
- reinforcement learning
- finite state
- policy iteration
- transition matrices
- heuristic search
- reachability analysis
- dynamic programming
- reinforcement learning algorithms
- state abstraction
- decentralized control
- real time dynamic programming
- markov decision process
- probabilistic planning
- partially observable markov decision processes
- average reward
- state variables
- classical planning
- belief state
- infinite horizon
- sufficient conditions
- dynamical systems
- multi agent
- action sets
- discounted reward
- reward function
- machine learning
- control strategy