The Impact of Task Underspecification in Evaluating Deep Reinforcement Learning.
Vindula JayawardanaCatherine TangSirui LiDajiang SuoCathy WuPublished in: NeurIPS (2022)
Keyphrases
- reinforcement learning
- function approximation
- high impact
- database
- factors that influence
- reinforcement learning algorithms
- multi agent
- expert systems
- probabilistic model
- state space
- optimal policy
- markov decision processes
- multi agent reinforcement learning
- temporal difference
- model free
- dynamic programming
- active learning
- database systems
- computer vision
- artificial intelligence
- learning algorithm
- machine learning