conftrace_

pessimistic value iteration

8 papers

Explore in graph

Also known as

PEVI

Co-occurring keywords

offline reinforcement learning (492) value iteration (162) robust mean estimation (11) markov decision process (790) minimax optimization (186) sample complexity (1169) uncertainty quantification (1393) function approximation (319) bellman target (1) adversarial agent (8)

Papers

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