Distributional Reward Estimation for Effective Multi-agent Deep Reinforcement Learning.
Jifeng HuYanchao SunHechang ChenSili HuangHaiyin PiaoYi ChangLichao SunPublished in: NeurIPS (2022)
Keyphrases
- reinforcement learning
- multi agent
- function approximation
- reinforcement learning algorithms
- state space
- temporal difference
- action selection
- eligibility traces
- dynamic environments
- multi agent systems
- markov decision processes
- high quality
- model free
- learning capabilities
- estimation accuracy
- accurate estimation
- transfer learning
- machine learning
- supervised learning
- mobile robot
- dynamic programming
- learning algorithm