Handling Incomplete Information in Policy Evaluation using Attribute Similarity.
Sowmya RavidasIndrakshi RayNicola ZannonePublished in: TPS-ISA (2020)
Keyphrases
- incomplete information
- policy evaluation
- least squares
- partial information
- temporal difference
- reinforcement learning
- model free
- variance reduction
- policy iteration
- missing information
- markov decision processes
- monte carlo
- statistical inference
- nash equilibria
- autonomous agents
- semi parametric
- first order logic
- reinforcement learning algorithms
- function approximation
- markov chain
- optimal policy