Human-in-the-Loop Synthesis for Partially Observable Markov Decision Processes.
Steven CarrNils JansenRalf WimmerJie FuUfuk TopcuPublished in: ACC (2018)
Keyphrases
- partially observable markov decision processes
- finite state
- belief space
- planning under uncertainty
- belief state
- stochastic domains
- continuous state
- dynamical systems
- partially observable stochastic games
- markov decision processes
- decision problems
- dynamic programming
- partial observability
- reinforcement learning
- optimal policy
- state space
- special case
- partially observable domains
- search space
- multi agent
- sequential decision making problems