Off-Policy Evaluation for Large Action Spaces via Policy Convolution.
Noveen SachdevaLequn WangDawen LiangNathan KallusJulian J. McAuleyPublished in: WWW (2024)
Keyphrases
- policy evaluation
- action space
- markov decision processes
- reinforcement learning
- policy iteration
- optimal policy
- temporal difference
- state space
- action selection
- markov decision problems
- least squares
- markov decision process
- model free
- finite state
- dynamic programming
- variance reduction
- reinforcement learning algorithms
- function approximation
- real valued
- average reward
- partially observable
- average cost
- infinite horizon
- monte carlo
- partially observable markov decision processes
- reward function
- multi agent systems
- semi parametric
- decision processes
- state action
- stochastic processes
- decision problems
- reinforcement learning methods
- machine learning