Short-Long Policy Evaluation with Novel Actions.
Hyunji Alex NamYash ChandakEmma BrunskillPublished in: CoRR (2024)
Keyphrases
- policy evaluation
- least squares
- temporal difference
- monte carlo
- model free
- reinforcement learning
- policy iteration
- markov decision processes
- variance reduction
- action selection
- function approximation
- situation calculus
- cost function
- step size
- decision theoretic
- computational complexity
- optimal solution
- partially observable
- semi parametric
- computer vision