Skip to content
conftrace_

multi-modal action distribution

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

offline reinforcement learning (2) energy-based normalizing flow (1) dispersive loss (1) generative policy (1) mode selection (1) expected return (1) maximum entropy reinforcement learning (1) flow-based model (1) soft q-function (1) robotic control (1)

Papers

D²PPO: Diffusion Policy Policy Optimization with Dispersive Loss AAAI 2026 One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow AAAI 2026 Learning on One Mode: Addressing Multi-modality in Offline Reinforcement Learning ICLR 2025 Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow NeurIPS 2024