Distributed Control using Reinforcement Learning with Temporal-Logic-Based Reward Shaping.
Ningyuan ZhangWenliang LiuCalin BeltaPublished in: L4DC (2022)
Keyphrases
- reward shaping
- reinforcement learning
- distributed control
- reinforcement learning algorithms
- complex domains
- multi agent reinforcement learning
- multi agent
- function approximation
- cooperative
- control architecture
- autonomous agents
- state space
- learning algorithm
- model free
- continuous state
- learning process
- information exchange
- transfer learning
- learning agent
- function approximators
- markov decision problems
- bayesian networks
- real time