Assessing the Impact of Distribution Shift on Reinforcement Learning Performance.
Ted FujimotoJoshua SuetterleinSamrat ChatterjeeAuroop R. GangulyPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- data distribution
- function approximation
- optimal policy
- learning algorithm
- model free
- machine learning
- high impact
- robot control
- evolutionary algorithm
- information systems
- least squares
- supervised learning
- dynamic programming
- transfer learning
- markov decision processes
- learning process
- spatial distribution
- decision making
- action selection
- real time