Reproduce “The Thing That We Tried Didn't Work Very Well : Deictic Representation in 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
Sarah Finney, Natalia Gardiol, Leslie Pack Kaelbling, Tim Oates
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.