activity
20242026
collaborators

6 papers

cs.LG2026

Joint Learning of Hierarchical Neural Options and Abstract World Model

Wasu Top Piriyakulkij, Wolfgang Lehrach, Kevin Ellis +1

Building agents that can perform new skills by composing existing skills is a long-standing goal of AI agent research. Towards this end, we investigate how to efficiently acquire a…

cs.CL2026

AutoHarness: improving LLM agents by automatically synthesizing a code harness

Xinghua Lou, Miguel Lázaro-Gredilla, Antoine Dedieu +3

Despite significant strides in language models in the last few years, when used as agents, such models often try to perform actions that are not just suboptimal for a given state,…

cs.AI2025

Code World Models for General Game Playing

Wolfgang Lehrach, Daniel Hennes, Miguel Lazaro-Gredilla +13

Large Language Models (LLMs) reasoning abilities are increasingly being applied to classical board and card games, but the dominant approach -- involving prompting for direct move…

cs.LG2025

Improving Transformer World Models for Data-Efficient RL

Antoine Dedieu, Joseph Ortiz, Xinghua Lou +5

We present three improvements to the standard model-based RL paradigm based on transformers: (a) "Dyna with warmup", which trains the policy on real and imaginary data, but only st…

cs.LG2025

Diffusion Model Predictive Control

Guangyao Zhou, Sivaramakrishnan Swaminathan, Rajkumar Vasudeva Raju +6

We propose Diffusion Model Predictive Control (D-MPC), a novel MPC approach that learns a multi-step action proposal and a multi-step dynamics model, both using diffusion models, a…

cs.LG2024

DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors

Joseph Ortiz, Antoine Dedieu, Wolfgang Lehrach +7

Learning from previously collected data via behavioral cloning or offline reinforcement learning (RL) is a powerful recipe for scaling generalist agents by avoiding the need for ex…