影响力指数

10.84/100

超过 33.5%

全站排名 #42,826

发表论文7 篇

平均评分4.9

年均产出2.3 篇/年

Riad Akrour

Researcher@INRIA·法国·OpenReview

研究方向

Deep Reinforcement Learning · Robotics · RL from Human feedback

StaQ: a Finite Memory Approach to Discrete Action Policy Mirror Descent

ICLR 2026Rejected

PB²: Preference Space Exploration via Population-Based Methods in Preference-Based Reinforcement Learning

ICLR 2026Rejected

A Continual Learning Perspective to Entropy Regularized Deep Reinforcement Learning

ICLR 2025Rejected

BiVWAC: Improving deep reinforcement learning algorithms using Bias-Variance Weighted Actor-Critic

ICLR 2025Withdrawn

合作者 (10)