Interpretable performance analysis towards offline reinforcement learning: A dataset perspective.
Chenyang XiBo TangJiajun ShenXinfu LiuFeiyu XiongXueying LiPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- benchmark datasets
- knowledge base
- real time
- machine learning
- learning algorithm
- database
- state space
- viewpoint
- policy search
- multi agent reinforcement learning
- function approximation
- dynamic programming
- real life
- object recognition
- object detection
- learning environment
- optimal policy
- markov decision processes
- face recognition
- reinforcement learning algorithms
- autonomous learning
- website
- neural network