Skip to content
conftrace_

pessimistic exploration

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

deep q-learning (2) uncertainty quantification (2) offline reinforcement learning (2) discrete control (1) gumbel noise (1) pessimistic value iteration (1) uncertainty estimation (1) ensemble method (1) minimax optimal (1) bellman error (1)

Papers

Double Gumbel Q-Learning NeurIPS 2023 Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters NeurIPS 2022 Is Pessimism Provably Efficient for Offline RL? ICML 2021