5 papers
Two-Bridge: Exclusive Objectives and Extended Horizon StarCraft II Benchmark
Sourav Panda, Tanmay Ambadkar, Shreyash Kale +2
The research community lacks a middle ground between StarCraft II full game and its mini-games. The full-game's sprawling state-action space renders reward signals sparse and noisy…
Automating the Refinement of Reinforcement Learning Specifications
Tanmay Ambadkar, ÄorÄe ŽikeliÄ, Abhinav Verma
Logical specifications have been shown to help reinforcement learning algorithms in achieving complex tasks. However, when a task is under-specified, agents might fail to learn use…
Non-Gaussian entanglement revealed by higher-order quadrature cumulants
Abhinav Verma, Olga Solodovnikova, Jonas S. Neergaard-Nielsen +1
Entanglement is central to quantum physics, yet detecting and exploiting it in non-Gaussian systems remains a major challenge. In continuous variable platforms, standard inseparabi…
Scalable architecture for measurement induced squeezed light interferometers
Abhinav Verma, Jacob Hastrup, Jonas S. Neergaard-Nielsen +1
Scalable interferometers lie at the heart of photonic quantum technologies, but their expansion has been fundamentally limited by optical losses that grow with circuit depth. Here,…
LTL-Constrained Policy Optimization with Cycle Experience Replay
Ameesh Shah, Cameron Voloshin, Chenxi Yang +3
Linear Temporal Logic (LTL) offers a precise means for constraining the behavior of reinforcement learning agents. However, in many settings where both satisfaction and optimality…