Search Results for author: Yevgen Chebotar

Found 23 papers, 6 papers with code

Robotic Offline RL from Internet Videos via Value-Function Pre-Training

no code implementations22 Sep 2023 Chethan Bhateja, Derek Guo, Dibya Ghosh, Anikait Singh, Manan Tomar, Quan Vuong, Yevgen Chebotar, Sergey Levine, Aviral Kumar

Our system, called V-PTR, combines the benefits of pre-training on video data with robotic offline RL approaches that train on diverse robot data, resulting in value functions and policies for manipulation tasks that perform better, act robustly, and generalize broadly.

Offline RL Reinforcement Learning (RL)

Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints

no code implementations2 Nov 2022 Anikait Singh, Aviral Kumar, Quan Vuong, Yevgen Chebotar, Sergey Levine

Both theoretically and empirically, we show that typical offline RL methods, which are based on distribution constraints fail to learn from data with such non-uniform variability, due to the requirement to stay close to the behavior policy to the same extent across the state space.

Atari Games Offline RL +2

Dual Generator Offline Reinforcement Learning

no code implementations2 Nov 2022 Quan Vuong, Aviral Kumar, Sergey Levine, Yevgen Chebotar

In this paper, we show that the issue of conflicting objectives can be resolved by training two generators: one that maximizes return, with the other capturing the ``remainder'' of the data distribution in the offline dataset, such that the mixture of the two is close to the behavior policy.

Offline RL reinforcement-learning +1

Data Sharing without Rewards in Multi-Task Offline Reinforcement Learning

no code implementations29 Sep 2021 Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Chelsea Finn, Sergey Levine, Karol Hausman

However, these benefits come at a cost -- for data to be shared between tasks, each transition must be annotated with reward labels corresponding to other tasks.

Multi-Task Learning Offline RL +2

Conservative Data Sharing for Multi-Task Offline Reinforcement Learning

no code implementations NeurIPS 2021 Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Sergey Levine, Chelsea Finn

We argue that a natural use case of offline RL is in settings where we can pool large amounts of data collected in various scenarios for solving different tasks, and utilize all of this data to learn behaviors for all the tasks more effectively rather than training each one in isolation.

Offline RL reinforcement-learning +1

MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale

no code implementations16 Apr 2021 Dmitry Kalashnikov, Jacob Varley, Yevgen Chebotar, Benjamin Swanson, Rico Jonschkowski, Chelsea Finn, Sergey Levine, Karol Hausman

In this paper, we study how a large-scale collective robotic learning system can acquire a repertoire of behaviors simultaneously, sharing exploration, experience, and representations across tasks.

reinforcement-learning Reinforcement Learning (RL)

Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills

no code implementations15 Apr 2021 Yevgen Chebotar, Karol Hausman, Yao Lu, Ted Xiao, Dmitry Kalashnikov, Jake Varley, Alex Irpan, Benjamin Eysenbach, Ryan Julian, Chelsea Finn, Sergey Levine

We consider the problem of learning useful robotic skills from previously collected offline data without access to manually specified rewards or additional online exploration, a setting that is becoming increasingly important for scaling robot learning by reusing past robotic data.

Q-Learning reinforcement-learning +1

Visionary: Vision architecture discovery for robot learning

no code implementations26 Mar 2021 Iretiayo Akinola, Anelia Angelova, Yao Lu, Yevgen Chebotar, Dmitry Kalashnikov, Jacob Varley, Julian Ibarz, Michael S. Ryoo

We propose a vision-based architecture search algorithm for robot manipulation learning, which discovers interactions between low dimension action inputs and high dimensional visual inputs.

Neural Architecture Search Robot Manipulation

Meta Learning via Learned Loss

no code implementations25 Sep 2019 Sarah Bechtle, Artem Molchanov, Yevgen Chebotar, Edward Grefenstette, Ludovic Righetti, Gaurav Sukhatme, Franziska Meier

We present a meta-learning method for learning parametric loss functions that can generalize across different tasks and model architectures.

Meta-Learning reinforcement-learning +1

Meta-Learning via Learned Loss

1 code implementation12 Jun 2019 Sarah Bechtle, Artem Molchanov, Yevgen Chebotar, Edward Grefenstette, Ludovic Righetti, Gaurav Sukhatme, Franziska Meier

This information shapes the learned loss function such that the environment does not need to provide this information during meta-test time.


Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience

no code implementations12 Oct 2018 Yevgen Chebotar, Ankur Handa, Viktor Makoviychuk, Miles Macklin, Jan Issac, Nathan Ratliff, Dieter Fox

In doing so, we are able to change the distribution of simulations to improve the policy transfer by matching the policy behavior in simulation and the real world.

Time-Contrastive Networks: Self-Supervised Learning from Video

6 code implementations23 Apr 2017 Pierre Sermanet, Corey Lynch, Yevgen Chebotar, Jasmine Hsu, Eric Jang, Stefan Schaal, Sergey Levine

While representations are learned from an unlabeled collection of task-related videos, robot behaviors such as pouring are learned by watching a single 3rd-person demonstration by a human.

Metric Learning reinforcement-learning +3

Path Integral Guided Policy Search

no code implementations3 Oct 2016 Yevgen Chebotar, Mrinal Kalakrishnan, Ali Yahya, Adrian Li, Stefan Schaal, Sergey Levine

We extend GPS in the following ways: (1) we propose the use of a model-free local optimizer based on path integral stochastic optimal control (PI2), which enables us to learn local policies for tasks with highly discontinuous contact dynamics; and (2) we enable GPS to train on a new set of task instances in every iteration by using on-policy sampling: this increases the diversity of the instances that the policy is trained on, and is crucial for achieving good generalization.

Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search

no code implementations3 Oct 2016 Ali Yahya, Adrian Li, Mrinal Kalakrishnan, Yevgen Chebotar, Sergey Levine

In this work, we explore distributed and asynchronous policy learning as a means to achieve generalization and improved training times on challenging, real-world manipulation tasks.

reinforcement-learning Reinforcement Learning (RL)

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