A Dataset Perspective on Offline Reinforcement Learning.
Kajetan SchweighoferMarius-Constantin DinuAndreas RadlerMarkus HofmarcherVihang Prakash PatilAngela Bitto-NemlingHamid Eghbal-zadehSepp HochreiterPublished in: CoLLAs (2022)
Keyphrases
- reinforcement learning
- function approximation
- benchmark datasets
- machine learning
- optimal control
- state space
- markov decision processes
- robotic control
- reinforcement learning algorithms
- learning classifier systems
- optimal policy
- supervised learning
- viewpoint
- object recognition
- multi agent
- training data
- real time
- learning process
- artificial intelligence
- data mining
- temporal difference
- policy search
- database