Distributed Control using Reinforcement Learning with Temporal-Logic-Based Reward Shaping.
Ningyuan ZhangWenliang LiuCalin BeltaPublished in: CoRR (2022)
Keyphrases
- reward shaping
- reinforcement learning
- distributed control
- reinforcement learning algorithms
- complex domains
- multi agent
- autonomous agents
- multi agent reinforcement learning
- function approximation
- cooperative
- state space
- markov decision processes
- control architecture
- policy search
- machine learning
- temporal difference
- markov decision problems
- decision making
- model free
- learning algorithm
- optimal policy
- function approximators
- dynamic programming
- domain theory
- information exchange
- decision makers
- dynamical systems