Reward-Relevance-Filtered Linear Offline Reinforcement Learning.
Angela ZhouPublished in: AISTATS (2024)
Keyphrases
- reinforcement learning
- function approximation
- function approximators
- reinforcement learning algorithms
- state space
- model free
- markov decision processes
- machine learning
- information retrieval
- learning algorithm
- reward function
- optimal policy
- eligibility traces
- temporal difference learning
- learning agent
- temporal difference
- transfer learning
- relevance feedback
- learning process
- multi agent
- neural network
- markov decision problems
- real time
- average reward
- robotic control
- low pass
- linear systems
- learning problems
- closed form
- test collection
- dynamic programming