Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Partially Equivariant Reinforcement Learning in Symmetry-Breaking Environments
Junwoo Chang, Minwoo Park, Joohwan Seo +3
Group symmetries provide a powerful inductive bias for reinforcement learning (RL), enabling efficient generalization across symmetric states and actions via group-invariant Markov…
cs.LG2025
Symmetry-Aware Steering of Equivariant Diffusion Policies: Benefits and Limits
Minwoo Park, Junwoo Chang, Jongeun Choi +1
Equivariant diffusion policies (EDPs) combine the generative expressivity of diffusion models with the strong generalization and sample efficiency afforded by geometric symmetries.…