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.
Imitation learning circumvents this problem and has been used with motion capture data to extract quadruped gaits for flat terrains.
1 code implementation • 12 Oct 2021 • Alex X. Lee, Coline Devin, Yuxiang Zhou, Thomas Lampe, Konstantinos Bousmalis, Jost Tobias Springenberg, Arunkumar Byravan, Abbas Abdolmaleki, Nimrod Gileadi, David Khosid, Claudio Fantacci, Jose Enrique Chen, Akhil Raju, Rae Jeong, Michael Neunert, Antoine Laurens, Stefano Saliceti, Federico Casarini, Martin Riedmiller, Raia Hadsell, Francesco Nori
We study the problem of robotic stacking with objects of complex geometry.
Ranked #2 on Skill Generalization on RGB-Stacking
no code implementations • 29 Sep 2021 • Abbas Abdolmaleki, Sandy Huang, Giulia Vezzani, Bobak Shahriari, Jost Tobias Springenberg, Shruti Mishra, Dhruva Tirumala, Arunkumar Byravan, Konstantinos Bousmalis, András György, 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.
no code implementations • 15 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
We highlight its strengths on standard MO benchmark problems and consider case studies in which we recast offline RL and learning from experts as MO problems.
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.
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.
Using domain adaptation methods to cross this "reality gap" requires a large amount of unlabelled real-world data, whilst domain randomization alone can waste modeling power.
Unsupervised domain adaptation (uDA) models focus on pairwise adaptation settings where there is a single, labeled, source and a single target domain.
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.
1 code implementation • 22 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.
Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks.
However, by focusing only on creating a mapping or shared representation between the two domains, they ignore the individual characteristics of each domain.
Ranked #1 on Domain Adaptation on Synth Objects-to-LINEMOD
Semi-Non-negative Matrix Factorization is a technique that learns a low-dimensional representation of a dataset that lends itself to a clustering interpretation.