4 papers
Spatial Attention: Adapting Execution Horizons for Diffusion Policies via Observation Sensitivity
Che-Sang Park, Junsu Ha, Jianlong Fu +1
Sampling action chunks via generative models has become a widely adopted methodology for robotic learning from demonstration. However, existing methods often struggle to balance re…
MATE: Solving Contextual Markov Decision Processes with Memory of Accumulated Transition Embeddings
Himchan Hwang, Hyeokju Jeong, Gene Chung +3
We propose MATE, a simple yet effective memory architecture for solving Contextual Markov Decision Processes (CMDPs), a family of MDPs parameterized by an unobserved context. In CM…
Value Gradient Sampler: Learning Invariant Value Functions for Equivariant Diffusion Sampling
Himchan Hwang, Hyeokju Jeong, Dong Kyu Shin +4
We propose the Value Gradient Sampler (VGS), a diffusion sampler parameterized by value functions. VGS generates samples from an unnormalized target density (i.e., energy) by evolv…
Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models
Sangwoong Yoon, Himchan Hwang, Dohyun Kwon +2
We present a maximum entropy inverse reinforcement learning (IRL) approach for improving the sample quality of diffusion generative models, especially when the number of generation…