Despite some success in mapless goal-driven navigation using deep reinforcement learning, there is an issue of insufficient experience utilization in deep reinforcement learning-based mapless ...

It was mid-October, peak leaf-peeping season in Hanover, New Hampshire, and Chad Markey was on a rare break between clinical rotations during his last year of medical school. He should have been ...

Figure 1. FIPO vs. baselines on AIME 2024. FIPO shows that pure RL training alone can outperform reproduced pure-RL baselines such as DAPO and DeepSeek-R1-Zero-32B, surpass o1-mini, and produce ...

This document is designed to help users quickly understand, use, and maintain the Python implementation of the Matrix-Sparsity-Based Pauli Decomposition (MSPD) algorithm. It specifies the function, ...

Explore the reinforcement learning algorithm that achieves performance comparable to GRPO in RLVR with minimal complexity. Learn how it works, why it’s effective, and its practical applications in RL ...

where System Throughput refers to the raw number of tokens processed per second, bottlenecked by 4 components of the whole RL system: rollout, training, data processing and I/O. Sample Efficiency ...

Combinatorial optimization underpins applications in artificial intelligence, logistics, and network design, yet classical techniques such as greedy search and dynamic programming struggle to balance ...

Hash tables are one of the oldest and simplest data structures for storing elements and supporting deletions and queries. Invented in 1953, they underly most computational systems. Yet despite their ...

I recently read a book to my 4½-year-old daughter that I immediately took out of her room and decided never to read again. That children’s book reminded me of an assignment I once had at the ...

Abstract: We present a simple performance bound for the greedy scheme in string optimization problems. Our approach generalizes the family of greedy curvature bounds established by Conforti and ...