arXiv Machine Learning By Jai Malegaonkar, Rohan Patil, Henrik I. Christensen

Reward Structure Shapes the Interaction Between Episodic Exploration and Neural Memory in Reinforcement Learning

Read the original on arXiv Machine Learning →

arXiv:2608. 05111v1 Announce Type: new Abstract: In partially observable reinforcement learning, agents face a dual bottleneck: they must explore to encounter rewarding states and retain that experience in memory to optimize their policies.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Jun 16

HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents

arXiv:2606. 16285v1 Announce Type: cross Abstract: Long-horizon agents rely on memory mechanisms to compress interaction history, but optimizing memory writing faces a distinct credit assignment challenge: a memory update may be rewarded or penalized due to downstream tool failures, noisy observations, or reasoning errors rather than its own contribution.

By Jiangze Yan, Yi Shen, Wenjing Zhang, Jieyun Huang, Zhaoxiang Liu, Ning Wang, Kai Wang, Shiguo Lian
Hugging Face Trending Papers
Jul 9

Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents

In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act. As trajectories grow, task requirements, environment facts, prior attempts, diagnoses, and open subgoals can be buried in the context window or pushed beyond it, failing to influence decisions when needed.