conftrace_

pessimistic value iteration

10 papers

Explore in graph

Also known as

PEVI

Co-occurring keywords · papers mentioning both

offline reinforcement learning (7) value iteration (3) markov decision process (3) sample complexity (3) robust mean estimation (2) minimax optimization (2) uncertainty quantification (2) function approximation (2) tiered reinforcement learning (1) distributed reinforcement learning (1)

Papers

Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning NeurIPS 2024 Exact Policy Recovery in Offline RL with Both Heavy-Tailed Rewards and Data Corruption AAAI 2024 Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning ICML 2024 Byzantine-Robust Online and Offline Distributed Reinforcement Learning AISTATS 2023 On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation AAAI 2023 Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism ICLR 2022 Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets ICML 2022 Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret NeurIPS 2022 Is Pessimism Provably Efficient for Offline RL? ICML 2021 Towards Instance-Optimal Offline Reinforcement Learning with Pessimism NeurIPS 2021