Reproduce “METTA: Memory-Enhanced Test-Time Adaptation for Meta-Reinforcement Learning” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Ali Najar, Hosein Hasani, Amir Kooshan Fattah, Yasamin Rajabi, Mahdieh Soleymani Baghshah
METTA gives meta-reinforcement-learning agents an online-updated memory within each episode and retrieves compact summaries across episodes, avoiding attention over every past interaction step. Its online updates help on sparse-reward PointMaze and hidden-goal ML1 Push, while versions perform similarly on observed-goal ML10. On PointMaze, coverage is 0.447 versus 0.250 for ECET; evidence is limited to tested settings.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.