Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance.
Mingxuan JingXiaojian MaWenbing HuangFuchun SunChao YangBin FangHuaping LiuPublished in: AAAI (2020)
Keyphrases
- reinforcement learning
- function approximation
- model free
- expert knowledge
- markov decision processes
- human experts
- machine learning
- reinforcement learning algorithms
- domain experts
- state space
- multi agent
- robot control
- learning algorithm
- temporal difference learning
- action selection
- robotic control
- transition model
- learning process
- expert systems
- learning problems
- case study
- real world
- real time
- policy search
- database