← Back to all news
arXiv Machine Learning

Training and Evaluating Ethical Reinforcement Learning Agents on Per-Episode Distributions

arXiv:2608. 14642v1 Announce Type: new Abstract: Reinforcement Learning (RL) agents trained on a single reward signal exploit the gap between the designed reward and the intended behavior.

Related stories

arXiv AI
Aug 17

Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation

arXiv:2608. 13564v1 Announce Type: new Abstract: Evaluating language-model agents at scale increasingly relies on a second language model as an automatic judge, because the gold signal, an executable environment reward, is expensive, slow, or unavailable at deployment time.

By Darragh Quinn, David Dylan, Roisin Healy, Fionn Carroll, Maeve Donnelly, Cormac Sheehan
llmsagentsfine-tuning
More like this →
arXiv Machine Learning
Aug 18

The Ethical Decision Head: Operationalizing Normative Ethics in Autonomous Vehicles via Reinforcement Learning from Human Feedback

arXiv:2608. 16710v1 Announce Type: new Abstract: As autonomous vehicles (AVs) approach Level 4 and Level 5 operational capability [SAE International, 2018], their on- board decision systems must handle not only safety-critical locomotion but also their subsequent moral weight.

By Thomas Mbrice, Ammar Ali, Sami Mian, Khai Hern Low, Eric Chen, Arshia Aghajani, Wolf Sch\"afer, Amin Shirangi
agentsreinforcement-learningroboticssafety
More like this →
arXiv Machine Learning
Aug 19

Debate Training Reduces Reward Hacking in RLAIF

The paper shows that fine‑tuning a large language model (LLM) with a debate framework—where a generator and a critic compete and a weaker LLM judge adjudicates—reduces reward hacking compared to standard reinforcement learning from AI feedback (RLAIF). In experiments on mathematics tasks, the debate approach keeps the judge’s performance stable, achieving a 45% higher peak validation accuracy than the RLAIF baseline and mitigating the rapid exploitation of judge errors. Additional findings indicate that weakening the judge speeds hacking unless countered by extra debate rounds, that debate can override misalignment prompts, and that word‑limit constraints on critiques help balance the game and prevent judge hacking. whyItMatters":"The study demonstrates a practical method to curb reward hacking in RL‑based AI systems, addressing a key obstacle for safely scaling AI oversight."

By Zachary Kenton, Lili Janzer, Rory Greig, Tian Huey Teh, Kirill Tyshchuk, Jonah Brown-Cohen, Harri Edwards, Senthooran Rajamanoharan, Noah Y. Siegel, Natasha Jaques, Rohin Shah
llmsagentsreinforcement-learningfine-tuningsafety
More like this →
arXiv Machine Learning
Aug 28

Shared Actors Need Not Share Critics: Effects of Value Mismatch in Parallel Reinforcement Learning

The paper investigates the problem of sharing a single critic across multiple parallel environments in reinforcement learning. It shows that when environments assign different expected returns to the same state, a shared critic must reconcile conflicting value targets, which can distort advantage estimates and misguide policy updates. The authors propose a simple fix—providing the critic with the environment index—demonstrating through bandit models and experiments on CartPole, MuJoCo, BipedalWalker, and 16 Procgen games that this conditional critic stabilizes learning and boosts returns, achieving a 40.8% improvement in aggregate normalized return on unseen levels.

By Zhenya Liu, Yang Meng, Zhuokai Zhao, Xuefeng Liu, Yuxin Chen
reinforcement-learning
More like this →
arXiv AI
Sep 7

What Does Multi-Harness RL Learn? Credit Assignment and Portability in Coding Agents

The study investigates how multi‑harness reinforcement learning (RL) affects coding agents by comparing two grouping strategies—Within (one group per task‑harness pair) and Cross (harnesses pooled within a task)—using a Qwen3‑8B policy trained on frozen task‑harness records from Aider, OpenHands, Qwen Code, and SWE‑agent. Across 24,000 sealed evaluations, the choice of evaluation harness dramatically increases solve rates (from 2.14 % to 9.27 %), while the grouping rule has a negligible effect. Both grouping rules yield similar gains on the same source harness, and Cross‑harness credit does not improve portability beyond Within‑harness credit, suggesting that multi‑harness RL reports should specify grouping boundaries and test on unseen harnesses.

By Chenqian Le, Jiayi Cheng, Qijia He, Runhao Li, Yinghao Li, Xupeng Chen
agentsreinforcement-learning
More like this →
arXiv AI
Aug 20

SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents

SkillGate is a method that trains agents to select the correct skill from a large slate during an episode by separating credit signals for skill selection and execution. It addresses the problem of selector credit starvation, where traditional outcome-rewarded RL fails to give sufficient credit to the skill-naming tokens, especially in long-horizon tasks. Experiments on five benchmarks show that SkillGate improves a 9B policy’s success rate from 40.8% to 53.2%, reduces exposure to misleading candidates, and requires fewer skill reads.

By Qingyao Li, Wenxiang Jiao, Shuai Shao, Kangning Zhang, Yuan Lu, Yi Guo, Weiwen Liu, Weinan Zhang, Yong Yu
agentsreinforcement-learningbenchmarks
More like this →
arXiv Machine Learning
Jul 13

SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions

arXiv:2607. 08925v1 Announce Type: new Abstract: Training reinforcement-learning agents directly on physical robots makes every fall costly, since a fall can damage the platform and cannot be undone like a simulator reset; the goal is therefore to minimize falls during training rather than trade them off against return, as constrained Markov decision process (MDP) formulations do.

By Elham Daneshmand, Majid Khadiv, Glen Berseth, Hsiu-Chin Lin
agentsreinforcement-learningroboticsbenchmarkssafety
More like this →