# Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning

arXiv: https://arxiv.org/abs/2603.25464 · HTML: https://mlsanity.com/paper/2603.25464/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 36 of its 44 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 30 of 36)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [Successor Features for Transfer in Reinforcement Learning](https://mlsanity.com/paper/1606.05312/) (2016)
- [π*0.6: a VLA That Learns From Experience](https://mlsanity.com/paper/2511.14759/) (2025)
- [Automatic Goal Generation for Reinforcement Learning Agents](https://mlsanity.com/paper/1705.06366/) (2017)
- [Skew-Fit: State-Covering Self-Supervised Reinforcement Learning](https://mlsanity.com/paper/1903.03698/) (2019)
- [URLB: Unsupervised Reinforcement Learning Benchmark](https://mlsanity.com/paper/2110.15191/) (2021)
- [Fast Task Inference with Variational Intrinsic Successor Features](https://mlsanity.com/paper/1906.05030/) (2019)
- [Discovering and Achieving Goals via World Models](https://mlsanity.com/paper/2110.09514/) (2021)
- [Learning One Representation to Optimize All Rewards](https://mlsanity.com/paper/2103.07945/) (2021)
- [APS: Active Pretraining with Successor Features](https://mlsanity.com/paper/2108.13956/) (2021)
- [Universal Successor Features Approximators](https://mlsanity.com/paper/1812.07626/) (2018)
- [C-Learning: Learning to Achieve Goals via Recursive Classification](https://mlsanity.com/paper/2011.08909/) (2020)
- [Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning](https://mlsanity.com/paper/2007.02832/) (2020)
- [Foundation Policies with Hilbert Representations](https://mlsanity.com/paper/2402.15567/) (2024)
- [METRA: Scalable Unsupervised RL with Metric-Aware Abstraction](https://mlsanity.com/paper/2310.08887/) (2023)
- [Does Zero-Shot Reinforcement Learning Exist?](https://mlsanity.com/paper/2209.14935/) (2022)
- [Learning Successor States and Goal-Dependent Values: A Mathematical Viewpoint](https://mlsanity.com/paper/2101.07123/) (2021)
- [Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models](https://mlsanity.com/paper/2504.11054/) (2025)
- [FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control](https://mlsanity.com/paper/2505.22642/) (2025)
- [BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning](https://mlsanity.com/paper/2511.04131/) (2025)
- [Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning](https://mlsanity.com/paper/2004.12974/) (2020)
- [TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning](https://mlsanity.com/paper/2510.00739/) (2025)
- [Zero-Shot Reinforcement Learning from Low Quality Data](https://mlsanity.com/paper/2309.15178/) (2023)
- [Fast Adaptation with Behavioral Foundation Models](https://mlsanity.com/paper/2504.07896/) (2025)
- [Proto Successor Measure: Representing the Behavior Space of an RL Agent](https://mlsanity.com/paper/2411.19418/) (2024)
- [Normalizing Flows are Capable Models for Continuous Control](https://mlsanity.com/paper/2505.23527/) (2025)

## Built on by (most cited first, 1 of 1)

- [Occupancy Modeling via Drifting: One-Step Generation Enables Direct Policy Extraction](https://mlsanity.com/paper/2610.19883/) (2026)

## Abstract (arXiv)

Zero-shot reinforcement learning (RL) algorithms aim to learn a family of policies from a reward-free dataset, and recover optimal policies for any reward function directly at test time. Naturally, the quality of the pretraining dataset determines the performance of the recovered policies across tasks. However, pre-collecting a relevant, diverse dataset without prior knowledge of the downstream tasks of interest remains a challenge. In this work, we study textitonline zero-shot RL for quadrupedal control on real robotic systems, building upon the Forward-Backward (FB) algorithm. We observe that undirected exploration yields low-diversity data, leading to poor downstream performance and rendering policies impractical for direct hardware deployment. Therefore, we introduce FB-MEBE, an online zero-shot RL algorithm that combines an unsupervised behavior exploration strategy with a regularization critic. FB-MEBE promotes exploration by maximizing the entropy of the achieved behavior distribution. Additionally, a regularization critic shapes the recovered policies toward more natural and physically plausible behaviors. We empirically demonstrate that FB-MEBE achieves and improved performance compared to other exploration strategies in a range of simulated downstream tasks, and that it renders natural policies that can be seamlessly deployed to hardware without further finetuning. Videos and code available on our website.