activity
20232025
most citedA Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learning

2 citations · 3 across the 9 of their papers we have counts for

collaborators
Showing 2023 · cs.LGShow all

1 paper · 2 filters

cs.LG2023

Multi-timestep models for Model-based Reinforcement Learning

Abdelhakim Benechehab, Giuseppe Paolo, Albert Thomas +2

In model-based reinforcement learning (MBRL), most algorithms rely on simulating trajectories from one-step dynamics models learned on data. A critical challenge of this approach i…