Search Results for author: Konstantinos Bousmalis

Found 14 papers, 5 papers with code

How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulation

no code implementations6 May 2022 Alex X. Lee, Coline Devin, Jost Tobias Springenberg, Yuxiang Zhou, Thomas Lampe, Abbas Abdolmaleki, Konstantinos Bousmalis

Our analysis, both in simulation and in the real world, shows that our approach is the best across data budgets, while standard offline RL from teacher rollouts is surprisingly effective when enough data is given.

Offline RL Reinforcement Learning (RL)

On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning

no code implementations15 Jun 2021 Abbas Abdolmaleki, Sandy H. Huang, Giulia Vezzani, Bobak Shahriari, Jost Tobias Springenberg, Shruti Mishra, Dhruva TB, Arunkumar Byravan, Konstantinos Bousmalis, Andras Gyorgy, Csaba Szepesvari, Raia Hadsell, Nicolas Heess, Martin Riedmiller

Many advances that have improved the robustness and efficiency of deep reinforcement learning (RL) algorithms can, in one way or another, be understood as introducing additional objectives or constraints in the policy optimization step.

Offline RL reinforcement-learning +1

Self-Supervised Sim-to-Real Adaptation for Visual Robotic Manipulation

no code implementations21 Oct 2019 Rae Jeong, Yusuf Aytar, David Khosid, Yuxiang Zhou, Jackie Kay, Thomas Lampe, Konstantinos Bousmalis, Francesco Nori

In this work, we learn a latent state representation implicitly with deep reinforcement learning in simulation, and then adapt it to the real domain using unlabeled real robot data.

Domain Adaptation reinforcement-learning +1

Off-Policy Evaluation via Off-Policy Classification

no code implementations NeurIPS 2019 Alex Irpan, Kanishka Rao, Konstantinos Bousmalis, Chris Harris, Julian Ibarz, Sergey Levine

However, for high-dimensional observations, such as images, models of the environment can be difficult to fit and value-based methods can make IS hard to use or even ill-conditioned, especially when dealing with continuous action spaces.

Classification General Classification +2

XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappings

4 code implementations ICLR 2018 Amélie Royer, Konstantinos Bousmalis, Stephan Gouws, Fred Bertsch, Inbar Mosseri, Forrester Cole, Kevin Murphy

Style transfer usually refers to the task of applying color and texture information from a specific style image to a given content image while preserving the structure of the latter.

Domain Adaptation Style Transfer +2

Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping

1 code implementation22 Sep 2017 Konstantinos Bousmalis, Alex Irpan, Paul Wohlhart, Yunfei Bai, Matthew Kelcey, Mrinal Kalakrishnan, Laura Downs, Julian Ibarz, Peter Pastor, Kurt Konolige, Sergey Levine, Vincent Vanhoucke

We extensively evaluate our approaches with a total of more than 25, 000 physical test grasps, studying a range of simulation conditions and domain adaptation methods, including a novel extension of pixel-level domain adaptation that we term the GraspGAN.

Domain Adaptation Industrial Robots +1

Domain Separation Networks

5 code implementations NeurIPS 2016 Konstantinos Bousmalis, George Trigeorgis, Nathan Silberman, Dilip Krishnan, Dumitru Erhan

However, by focusing only on creating a mapping or shared representation between the two domains, they ignore the individual characteristics of each domain.

Domain Generalization Unsupervised Domain Adaptation

A deep matrix factorization method for learning attribute representations

no code implementations10 Sep 2015 George Trigeorgis, Konstantinos Bousmalis, Stefanos Zafeiriou, Bjoern W. Schuller

Semi-Non-negative Matrix Factorization is a technique that learns a low-dimensional representation of a dataset that lends itself to a clustering interpretation.

Attribute Clustering

Cannot find the paper you are looking for? You can Submit a new open access paper.