PIMbot: Policy and Incentive Manipulation for Multi-Robot Reinforcement Learning in Social Dilemmas.
Shahab NikkhooZexin LiAritra SamantaYufei LiCong LiuPublished in: IROS (2023)
Keyphrases
- multi robot
- reinforcement learning
- optimal policy
- policy search
- real robot
- path planning
- mobile robot
- action selection
- multi robot systems
- markov decision process
- action space
- function approximators
- multi robot exploration
- markov decision processes
- policy gradient
- search and rescue
- control policy
- function approximation
- robotic systems
- partially observable
- potential field
- motion planning
- reinforcement learning algorithms
- partially observable markov decision processes
- policy iteration
- state space
- reward function
- initially unknown
- robot soccer
- coalitional game theory
- multi robot cooperative
- learning algorithm
- dynamic programming
- average reward
- multiple robots
- infinite horizon
- long run
- map building
- uncertain environments
- agent learns
- formation control
- real time
- robot teams
- multi agent
- object detection
- event detection
- model free