Balatro, a 2024 roguelike deckbuilder, presents three difficulties that have historically derailed reinforcement learning methods: a 3,000-action state-dependent action space, horizons of several hundred decisions with sparse rewards, and pervasive stochasticity in both card draws and shop generation. Published RL resu...
Vision2Code is introduced, a multi-domain, reference-code-free benchmark containing 539 test examples from 15 different datasets, spanning charts and plots, geometry, graphs, scientific diagrams, documents and 3D spatial scenes, which highlights the variability across domains of existing image-to-code generation models...
Large language model (LLM) planners can decompose natural-language instructions and select reusable robot skills, but choosing the correct skill does not guarantee successful physical execution. This gap is especially important in humanoid loco-manipulation, where errors during approach, grasping, transport, or placeme...
Ajay Vikram Periasami, Xin Luo, Hao-Yu Li et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.