CROP: Towards Distributional-Shift Robust Reinforcement Learning using Compact Reshaped Observation Processing.
Philipp AltmannFabian RitzLeonard FeuchtingerJonas NüßleinClaudia Linnhoff-PopienThomy PhanPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- real time
- function approximation
- learning process
- data processing
- information processing
- dynamic programming
- reinforcement learning algorithms
- parameter tuning
- evaluation function
- markov decision processes
- transfer learning
- hidden markov models
- multiscale
- information systems
- learning algorithm
- machine learning
- data sets