Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation.
Haruka KiyoharaRen KishimotoKosuke KawakamiKen KobayashiKazuhide NakataYuta SaitoPublished in: ICLR (2024)
Keyphrases
- policy evaluation
- least squares
- temporal difference
- monte carlo
- reinforcement learning
- model free
- markov decision processes
- policy iteration
- function approximation
- matrix inversion
- variance reduction
- optimal policy
- computational complexity
- decision making
- learning algorithm
- machine learning
- partially observable markov decision processes
- neural network