activity
20242026
collaborators

10 papers

cs.AI2026

RPRA: Predicting an LLM-Judge for Efficient but Performant Inference

Dylan R. Ashley, Gaël Le Lan, Changsheng Zhao +7

Large language models (LLMs) face a fundamental trade-off between computational efficiency (e.g., number of parameters) and output quality, especially when deployed on computationa…

cs.LG2026

Efficient Morphology-Control Co-Design via Stackelberg Proximal Policy Optimization

Yanning Dai, Yuhui Wang, Dylan R. Ashley +1

Morphology-control co-design concerns the coupled optimization of an agent's body structure and control policy. This problem exhibits a bi-level structure, where the control dynami…

cs.RO2026

RACAS: Controlling Diverse Robots With a Single Agentic System

Dylan R. Ashley, Jan Przepióra, Yimeng Chen +5

Many robotic platforms expose an API through which external software can command their actuators and read their sensors. However, transitioning from these low-level interfaces to h…

stat.ML2025

On the Convergence and Stability of Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning, and Online Decision Transformers

Miroslav Å trupl, Oleg Szehr, Francesco Faccio +3

This article provides a rigorous analysis of convergence and stability of Episodic Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning and Online Decision Tran…

cs.LG2025

Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning

Yuhui Wang, Qingyuan Wu, Dylan R. Ashley +4

The Value Iteration Network (VIN) is an end-to-end differentiable neural network architecture for planning. It exhibits strong generalization to unseen domains by incorporating a d…

cs.LG2025

Upside Down Reinforcement Learning with Policy Generators

Jacopo Di Ventura, Dylan R. Ashley, Vincent Herrmann +2

Upside Down Reinforcement Learning (UDRL) is a promising framework for solving reinforcement learning problems which focuses on learning command-conditioned policies. In this work,…