open-ended-environments

Tag

Cards List
#open-ended-environments

Joint Agent Memory and Exploration Learning via Novelty Signals

Hugging Face Daily Papers · 5d ago Cached

This paper introduces JAMEL, a framework that jointly trains agentic memory and exploration policies using novelty signals, enabling efficient exploration in open-ended environments with reduced computational costs.

0 favorites 0 likes
#open-ended-environments

GRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from Zero

arXiv cs.LG · 2026-05-18 Cached

GRLO introduces a novel reinforcement learning post-training method that achieves strong generalization across multiple domains (math, code, etc.) from only 5K prompts and 22.7 GPU hours, significantly outperforming in-domain RLVR baselines in efficiency and data requirements.

0 favorites 0 likes
← Back to home

Submit Feedback