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