paper-with-me

홈 › Papers

Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation

2024-12-09 · Egor Cherepanov, Nikita Kachaev, Artem Zholus, Alexey K. Kovalev, Aleksandr I. Panov

The incorporation of memory into agents is essential for numerous tasks within the domain of Reinforcement Learning (RL). In particular, memory is paramount for tasks that require the utilization of past information, adaptation to novel environments, and improved sample efficiency. However, the term ``memory'' encompasses a wide range of concepts, which, coupled with the lack of a unified methodology for validating an agent's memory, leads to erroneous judgments about agents' memory capabilities and prevents objective comparison with other memory-enhanced agents. This paper aims to streamline the concept of memory in RL by providing practical precise definitions of agent memory types, such as long-term versus short-term memory and declarative versus procedural memory, inspired by cognitive science. Using these definitions, we categorize different classes of agent memory, propose a robust experimental methodology for evaluating the memory capabilities of RL agents, and standardize evaluations. Furthermore, we empirically demonstrate the importance of adhering to the proposed methodology when evaluating different types of agent memory by conducting experiments with different RL agents and what its violation leads to.

📄 PDF Abstract BibTeX arXiv:2412.06531

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Agent-ScanKit: Unraveling Memory and Reasoning of Multimodal Agents via Sensitivity Perturbations

2025-10-01 · Pengzhou Cheng, Lingzhong Dong, Zeng Wu, Zongru Wu 외 arxiv

Although numerous strategies have recently been proposed to enhance the autonomous interaction capabilities of multimodal agents in graphical user interface (GUI), their reliability remains limited when faced with comple…

TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents

2026-01-06 · Kai Li, Xuanqing Yu, Ziyi Ni, Yi Zeng 외 arxiv

Long-horizon conversational agents have to manage ever-growing interaction histories that quickly exceed the finite context windows of large language models (LLMs). Existing memory frameworks provide limited support for …

A linguistically-motivated evaluation methodology for unraveling model's abilities in reading comprehension tasks

2025-01-29 · Elie Antoine, Frédéric Béchet, Géraldine Damnati, Philippe Langlais

We introduce an evaluation methodology for reading comprehension tasks based on the intuition that certain examples, by the virtue of their linguistic complexity, consistently yield lower scores regardless of model size …

Reading Comprehension

Reinforcement Learning for Hardware Security: Opportunities, Developments, and Challenges

2022-08-29 · Satwik Patnaik, Vasudev Gohil, Hao Guo, Jeyavijayan 외

Reinforcement learning (RL) is a machine learning paradigm where an autonomous agent learns to make an optimal sequence of decisions by interacting with the underlying environment. The promise demonstrated by RL-guided w…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents

2026-04-21 · Md Nayem Uddin, Kumar Shubham, Eduardo Blanco, Chitta Baral 외 arxiv

Personalized agents that interact with users over long periods must maintain persistent memory across sessions and update it as circumstances change. However, existing benchmarks predominantly frame long-term memory eval…