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