paper-with-me

Papers

Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings

2024-02-27 · Kevin Frans, Seohong Park, Pieter Abbeel, Sergey Levine

Can we pre-train a generalist agent from a large amount of unlabeled offline trajectories such that it can be immediately adapted to any new downstream tasks in a zero-shot manner? In this work, we present a functional reward encoding (FRE) as a general, scalable solution to this zero-shot RL problem. Our main idea is to learn functional representations of any arbitrary tasks by encoding their state-reward samples using a transformer-based variational auto-encoder. This functional encoding not only enables the pre-training of an agent from a wide diversity of general unsupervised reward functions, but also provides a way to solve any new downstream tasks in a zero-shot manner, given a small number of reward-annotated samples. We empirically show that FRE agents trained on diverse random unsupervised reward functions can generalize to solve novel tasks in a range of simulated robotic benchmarks, often outperforming previous zero-shot RL and offline RL methods. Code for this project is provided at: https://github.com/kvfrans/fre

📄 PDF Abstract BibTeX arXiv:2402.17135

Code (1)

kvfrans/fre 공식 구현 jax

Tasks

DiversityOffline RLreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning

2025-11-06 · Yitang Li, Zhengyi Luo, Tonghe Zhang, Cunxi Dai 외 arxiv

Building Behavioral Foundation Models (BFMs) for humanoid robots has the potential to unify diverse control tasks under a single, promptable generalist policy. However, existing approaches are either exclusively deployed…

Reinforcement Learning

TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning

2025-10-01 · Marco Bagatella, Matteo Pirotta, Ahmed Touati, Alessandro Lazaric 외 arxiv

Latent prediction--where agents learn by predicting their own latents--has emerged as a powerful paradigm for training general representations in machine learning. In reinforcement learning (RL), this approach has been e…

Reinforcement Learning

Bounding the Optimal Value Function in Compositional Reinforcement Learning

2023-03-05 · Jacob Adamczyk, Volodymyr Makarenko, Argenis Arriojas, Stas Tiomkin 외

In the field of reinforcement learning (RL), agents are often tasked with solving a variety of problems differing only in their reward functions. In order to quickly obtain solutions to unseen problems with new reward fu…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Fast Adaptation with Behavioral Foundation Models

2025-04-10 · Harshit Sikchi, Andrea Tirinzoni, Ahmed Touati, Yingchen Xu 외

Unsupervised zero-shot reinforcement learning (RL) has emerged as a powerful paradigm for pretraining behavioral foundation models (BFMs), enabling agents to solve a wide range of downstream tasks specified via reward fu…

Reinforcement Learning (RL)

Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning

2026-03-26 · Jiajun Hu, Nuria Armengol Urpi, Jin Cheng, Stelian Coros 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 pre…

Reinforcement Learning