12 papers
Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates
Anish Diwan, Davide Tateo, Christopher E. Mower +3
Inverse reinforcement learning (IRL) is typically formulated as maximizing entropy subject to matching the distribution of expert trajectories. Classical (dual-ascent) IRL guarante…
Behavior-Constrained Reinforcement Learning with Receding-Horizon Credit Assignment for High-Performance Control
Siwei Ju, Jan Tauberschmidt, Oleg Arenz +2
Learning high-performance control policies that remain consistent with expert behavior is a fundamental challenge in robotics. Reinforcement learning can discover high-performing s…
Boosting deep Reinforcement Learning using pretraining with Logical Options
Zihan Ye, Phil Chau, Raban Emunds +5
Deep reinforcement learning agents are often misaligned, as they over-exploit early reward signals. Recently, several symbolic approaches have addressed these challenges by encodin…
GaussTwin: Unified Simulation and Correction with Gaussian Splatting for Robotic Digital Twins
Yichen Cai, Paul Jansonnie, Cristiana de Farias +2
Digital twins promise to enhance robotic manipulation by maintaining a consistent link between real-world perception and simulation. However, most existing systems struggle with th…
Floating-Base Deep Lagrangian Networks
Lucas Schulze, Juliano Decico Negri, Victor Barasuol +4
Grey-box methods for system identification combine deep learning with physics-informed constraints, capturing complex dependencies while improving out-of-distribution generalizatio…
Discrete Variational Autoencoding via Policy Search
Michael Drolet, Firas Al-Hafez, Aditya Bhatt +2
Discrete latent bottlenecks in variational autoencoders (VAEs) offer high bit efficiency and can be modeled with autoregressive discrete distributions, enabling parameter-efficient…