4 papers
Adaptive Reinforcement Learning for Unobservable Random Delays
John Wikman, Alexandre Proutiere, David Broman
In standard reinforcement learning (RL) settings, the interaction between the agent and the environment is typically modeled as a Markov decision process (MDP), which assumes that…
Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning
Stefan Stojanovic, Alexandre Proutiere
Hierarchical reinforcement learning can improve generalization by decomposing long-horizon decision-making into simpler subproblems. However, existing approaches often rely on rest…
Advantage-Guided Diffusion for Model-Based Reinforcement Learning
Daniele Foffano, Arvid Eriksson, David Broman +2
Model-based reinforcement learning (MBRL) with autoregressive world models suffers from compounding errors, whereas diffusion world models mitigate this by generating trajectory se…
Receding-Horizon Control via Drifting Models
Daniele Foffano, Alessio Russo, Alexandre Proutiere
We study the problem of trajectory optimization in settings where the system dynamics are unknown and it is not possible to simulate trajectories through a surrogate model. When an…