Logic-based Reward Shaping for Multi-Agent Reinforcement Learning.
Ingy Elsayed-AlyLu FengPublished in: CoRR (2022)
Keyphrases
- multi agent reinforcement learning
- reward shaping
- reinforcement learning
- learning agent
- complex domains
- reinforcement learning algorithms
- multi agent learning
- multi agent
- learning agents
- state space
- stochastic games
- knowledge representation
- optimal policy
- function approximation
- model free
- markov decision processes
- learning process
- learning algorithm
- temporal difference
- dynamic programming
- multi agent systems
- optimal control
- machine learning
- markov decision process
- cooperative