Forager: a lightweight testbed for continual learning with partial observability in RL

arXiv:2605.01131v2 Announce Type: replace Abstract: In continual reinforcement learning (CRL), good performance requires never-ending learning, acting, and exploration in a big, partially observable world. Most CRL experiments have focused on loss of plasticity---the inability to keep learning---in one-off experiments where some unobservable non-stationarity is added to classic fully observable MDPs. Further, these experiments rarely consider the role of partial observability and the importance of CRL agents that use memory or recurrence. One potential reason for this focus on mitigating loss of plasticity without considering partial observability is that many partially-observable CRL environments are prohibitively expensive. In this paper, we introduce Forager, a lightweight partially-observable CRL environment with a constant memory footprint. We provide a set of experiments and sample tasks demonstrating that Forager is challenging for current CRL agents and yet also allows for in-depth study of those agents. We demonstrate that agents exhibit loss of plasticity, proposed mitigations can help, but that most useful is to leverage state construction. We conclude with a variant of Forager that generates an unending stream of new tasks to learn that clearly highlights the limitations of current CRL agents.

Abstract:In continual reinforcement learning (CRL), good performance requires never-ending learning, acting, and exploration in a big, partially observable world. Most CRL experiments have focused on loss of plasticity---the inability to keep learning---in one-off experiments where some unobservable non-stationarity is added to classic fully observable MDPs. Further, these experiments rarely consider the role of partial observability and the importance of CRL agents that use memory or recurrence. One potential reason for this focus on mitigating loss of plasticity without considering partial observability is that many partially-observable CRL environments are prohibitively expensive. In this paper, we introduce Forager, a lightweight partially-observable CRL environment with a constant memory footprint. We provide a set of experiments and sample tasks demonstrating that Forager is challenging for current CRL agents and yet also allows for in-depth study of those agents. We demonstrate that agents exhibit loss of plasticity, proposed mitigations can help, but that most useful is to leverage state construction. We conclude with a variant of Forager that generates an unending stream of new tasks to learn that clearly highlights the limitations of current CRL agents.

Published in the Reinforcement Learning Journal (RLJ), 2026. 25 pages, 9 figures, 11 tables. Code: this https URL and this https URL

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

arXiv:2605.01131 [cs.LG]

(or arXiv:2605.01131v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2605.01131 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

analiza aiqbench

Forager: a lightweight testbed for continual learning with partial observability in RL

Subiecte conexe