Reward Shaping Based Federated Reinforcement Learning.
Yiqiu HuYun HuaWenyan LiuJun ZhuPublished in: IEEE Access (2021)
Keyphrases
- reward shaping
- reinforcement learning
- reinforcement learning algorithms
- complex domains
- state space
- markov decision problems
- function approximation
- model free
- temporal difference
- markov decision processes
- transfer learning
- neural network
- partially observable
- machine learning
- optimal policy
- learning agent
- dynamic programming
- agent learns