The Impact of Task Underspecification in Evaluating Deep Reinforcement Learning.
Vindula JayawardanaCatherine TangSirui LiDajiang SuoCathy WuPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- high impact
- machine learning
- markov decision processes
- state space
- multi agent
- databases
- neural network
- computer vision
- learning process
- evolutionary algorithm
- real world
- optimal policy
- function approximation
- temporal difference
- reinforcement learning algorithms
- factors that influence
- database