papers

Publications (15)

cs.LG2024

Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learning

Norman Di Palo, Leonard Hasenclever, Jan Humplik +1

We introduce Diffusion Augmented Agents (DAAG), a novel framework that leverages large language models, vision language models, and diffusion models to improve sample efficiency an…

cs.RO2024

Learning to Learn Faster from Human Feedback with Language Model Predictive Control

Jacky Liang, Fei Xia, Wenhao Yu +47

Large language models (LLMs) have been shown to exhibit a wide range of capabilities, such as writing robot code from language commands -- enabling non-experts to direct robot beha…

cs.RO2025

Gemini Robotics: Bringing AI into the Physical World

Gemini Robotics Team, Saminda Abeyruwan, Joshua Ainslie +115

Recent advancements in large multimodal models have led to the emergence of remarkable generalist capabilities in digital domains, yet their translation to physical agents such as…

cs.RO2022

NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields

Arunkumar Byravan, Jan Humplik, Leonard Hasenclever +8

We present a system for applying sim2real approaches to "in the wild" scenes with realistic visuals, and to policies which rely on active perception using RGB cameras. Given a shor…

cs.LG2021

Importance Weighted Policy Learning and Adaptation

Alexandre Galashov, Jakub Sygnowski, Guillaume Desjardins +5

The ability to exploit prior experience to solve novel problems rapidly is a hallmark of biological learning systems and of great practical importance for artificial ones. In the m…

cs.RO2024

Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning

Dhruva Tirumala, Markus Wulfmeier, Ben Moran +13

We apply multi-agent deep reinforcement learning (RL) to train end-to-end robot soccer policies with fully onboard computation and sensing via egocentric RGB vision. This setting r…

cs.RO2025

Proc4Gem: Foundation models for physical agency through procedural generation

Yixin Lin, Jan Humplik, Sandy H. Huang +18

In robot learning, it is common to either ignore the environment semantics, focusing on tasks like whole-body control which only require reasoning about robot-environment contacts,…

cs.RO2022

Forgetting and Imbalance in Robot Lifelong Learning with Off-policy Data

Wenxuan Zhou, Steven Bohez, Jan Humplik +5

Robots will experience non-stationary environment dynamics throughout their lifetime: the robot dynamics can change due to wear and tear, or its surroundings may change over time.…

cs.LG2019

Meta reinforcement learning as task inference

Jan Humplik, Alexandre Galashov, Leonard Hasenclever +3

Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There is considerable interest in designing reinforcement learning…

cs.RO2024

Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning

Tuomas Haarnoja, Ben Moran, Guy Lever +25

We investigate whether Deep Reinforcement Learning (Deep RL) is able to synthesize sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be compo…

cs.LG2023

SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration

Giulia Vezzani, Dhruva Tirumala, Markus Wulfmeier +13

The ability to effectively reuse prior knowledge is a key requirement when building general and flexible Reinforcement Learning (RL) agents. Skill reuse is one of the most common a…

q-bio.NC2016

Semiparametric energy-based probabilistic models

Jan Humplik, Gašper Tkačik

Probabilistic models can be defined by an energy function, where the probability of each state is proportional to the exponential of the state's negative energy. This paper conside…

physics.bio-ph2021

Inferring couplings in networks across order-disorder phase transitions

Vudtiwat Ngampruetikorn, Vedant Sachdeva, Johanna Torrence +3

Statistical inference is central to many scientific endeavors, yet how it works remains unresolved. Answering this requires a quantitative understanding of the intrinsic interplay…

cs.RO2023

Language to Rewards for Robotic Skill Synthesis

Wenhao Yu, Nimrod Gileadi, Chuyuan Fu +17

Large language models (LLMs) have demonstrated exciting progress in acquiring diverse new capabilities through in-context learning, ranging from logical reasoning to code-writing.…

cs.RO2022

Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors

Steven Bohez, Saran Tunyasuvunakool, Philemon Brakel +18

We investigate the use of prior knowledge of human and animal movement to learn reusable locomotion skills for real legged robots. Our approach builds upon previous work on imitati…