10 papers
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…
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…
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…
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…
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…
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,…