Datasets and Benchmarks for Offline Safe Reinforcement Learning.
Zuxin LiuZijian GuoHaohong LinYihang YaoJiacheng ZhuZhepeng CenHanjiang HuWenhao YuTingnan ZhangJie TanDing ZhaoPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- machine learning
- real time
- database
- learning algorithm
- benchmark datasets
- state space
- dynamic programming
- learning process
- databases
- markov decision processes
- model free
- training data
- uci machine learning repository
- information retrieval
- synthetic and real datasets
- temporal difference
- experimental results on real world
- training dataset
- benchmark suite
- optimal control
- learning problems
- data mining algorithms
- mobile robot
- multi agent
- knowledge base
- information systems
- neural network