← Back to all news
arXiv AI By Dogan Urgun

GARDEN: Generalist Autonomous Reward Design Through Evidence Navigation for Cooperative Multi-Agent Reinforcement Learning

Read the original on arXiv AI →

The paper introduces GARDEN, a framework that uses large language models to autonomously design a single reward program for cooperative multi‑agent reinforcement learning tasks. By navigating evidence from environment code, training logs, and agent behavior, the reward is tested and finalized without altering the learning algorithm. Experiments on Overcooked and SMAX benchmarks show that the autonomously engineered reward improves task returns by up to 58.2% and win rates by up to 89.9% compared to default rewards, outperforming prior methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 18

UnifiedPlayers: Enhance Tool-Integrated Reasoning in Agentic Reinforcement Learning

UnifiedPlayers is a cooperative framework that jointly adapts planning, execution, and evaluation for tool-integrated reinforcement learning agents. It consists of a Planning Player that generates tasks, an Execution Player that creates multi-turn trajectories with Python tool calls, and an Evaluation Player that builds executable verifiers, all coordinated by role‑specific rewards under GRPO. The approach outperforms prior baselines on mathematical and general reasoning benchmarks and yields a verifier with high adversarial detection accuracy and more discriminative reward signals.

By Wenjie Liao, Liangjie Zhao, Zehong Cao
agentsreinforcement-learningbenchmarkssafety
More like this →
arXiv AI
Sep 28

SUN: Agentic Robot Policy Learning with Persistent Task Programs

The paper introduces SUN (Semantically UNified) Programs, typed executables that translate grounded relations into optimal control objectives, satisfaction predicates, and learning rewards. Using the Kuafu harness, a foundation model orchestrates scene preparation, verification, residual reinforcement learning, and data generation, repairing candidate programs and calibrating reward weights. Across nine multi‑stage manipulation tasks, Kuafu achieves an 82.03% success rate, outperforms learned baselines, generates demonstrations 10.57× faster than human teleoperation, and transfers zero‑shot to physical Franka and Kinova robots.

By Weiqi Wang, Zhi Li, Yudong Lei, David Martinez, Xiaofeng Gao, Yuxin Jiang, Chenfanfu Jiang, Yingnian Wu, Demetri Terzopoulos, Ran Gong
agentsreinforcement-learningrobotics
More like this →
arXiv Machine Learning
Jun 2

RDA: Reward Design Agent for Reinforcement Learning

arXiv:2606. 01672v1 Announce Type: new Abstract: Reinforcement learning has enabled the acquisition of impressive robotic skills, but typically requires hand-crafted reward functions that are slow to design and difficult to align with human intentions.

By Hojoon Lee, Ajay Subramanian, Ben Abbatematteo, Vijay Veerabadran, Pedro Matias, Karl Ridgeway, Nitin Kamra
llmsagentsreinforcement-learningroboticsmultimodal
More like this →