Score: 0

SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation

Published: December 10, 2025 | arXiv ID: 2512.10042v1

By: Jongmin Lee, Meiqi Sun, Pieter Abbeel

Potential Business Impact:

Teaches robots to learn new skills faster.

Business Areas:
SEM Advertising, Internet Services, Sales and Marketing

In the unsupervised pre-training for reinforcement learning, the agent aims to learn a prior policy for downstream tasks without relying on task-specific reward functions. We focus on state entropy maximization (SEM), where the goal is to learn a policy that maximizes the entropy of the state stationary distribution. In this paper, we introduce SEMDICE, a principled off-policy algorithm that computes an SEM policy from an arbitrary off-policy dataset, which optimizes the policy directly within the space of stationary distributions. SEMDICE computes a single, stationary Markov state-entropy-maximizing policy from an arbitrary off-policy dataset. Experimental results demonstrate that SEMDICE outperforms baseline algorithms in maximizing state entropy while achieving the best adaptation efficiency for downstream tasks among SEM-based unsupervised RL pre-training methods.

Page Count
26 pages

Category
Computer Science:
Machine Learning (CS)