Multiagent Rollout and Policy Iteration for POMDP with Application to Multi-Robot Repair Problems.
Sushmita BhattacharyaSiva KailasSahil BadyalStephanie GilDimitri P. BertsekasPublished in: CoRL (2020)
Keyphrases
- multi robot
- markov decision processes
- policy iteration
- multi agent
- markov decision process
- reinforcement learning
- mobile robot
- partially observable markov decision processes
- planning under uncertainty
- finite state
- markov decision problems
- dec pomdps
- least squares
- multi agent systems
- cooperative
- multi robot systems
- path planning
- computer vision
- policy evaluation