Skip to content
conftrace_

conservative algorithm

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

performance constraint (1) multi-step reinforcement learning (1) multi-step learning (1) offline pretraining (1) dataset quality (1) low quality data (1) zero-shot reinforcement learning (1) successor feature (1) contextual bandit (1) regret bound (1)

Papers

Zero-Shot Reinforcement Learning from Low Quality Data NeurIPS 2024 Contextual Conservative Interleaving Bandits ICML 2023 Revisiting Peng’s Q($λ$) for Modern Reinforcement Learning ICML 2021