Improvement and Evaluation of the Policy Legibility in Reinforcement Learning.
Yanyu LiuYifeng ZengBiyang MaYinghui PanHuifan GaoXiaohan HuangPublished in: AAMAS (2023)
Keyphrases
- reinforcement learning
- optimal policy
- markov decision process
- action selection
- multi agent
- function approximation
- evaluation model
- partially observable environments
- policy search
- transition model
- approximate dynamic programming
- control policies
- evaluation method
- markov decision processes
- state space
- infinite horizon
- data sets
- evaluation methods
- function approximators
- evaluation criteria
- reinforcement learning problems
- neural network