Multiagent Rollout and Policy Iteration for POMDP with Application to Multi-Robot Repair Problems.
Sushmita BhattacharyaSiva KailasSahil BadyalStephanie GilDimitri P. BertsekasPublished in: CoRR (2020)
Keyphrases
- multi robot
- policy iteration
- markov decision process
- multi agent
- markov decision processes
- reinforcement learning
- mobile robot
- planning under uncertainty
- optimal policy
- finite state
- path planning
- real time
- policy evaluation
- dynamical systems
- state space
- infinite horizon
- model free
- temporal difference
- cooperative
- markov decision problems