Search Results for author: Shikhar Bahl

Found 15 papers, 5 papers with code

Visual Reinforcement Learning with Imagined Goals

2 code implementations NeurIPS 2018 Ashvin Nair, Vitchyr Pong, Murtaza Dalal, Shikhar Bahl, Steven Lin, Sergey Levine

For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be able to learn broadly applicable and general-purpose skill repertoires.

reinforcement-learning Reinforcement Learning (RL) +1

Contextual Imagined Goals for Self-Supervised Robotic Learning

1 code implementation23 Oct 2019 Ashvin Nair, Shikhar Bahl, Alexander Khazatsky, Vitchyr Pong, Glen Berseth, Sergey Levine

When the robot's environment and available objects vary, as they do in most open-world settings, the robot must propose to itself only those goals that it can accomplish in its present setting with the objects that are at hand.

reinforcement-learning Reinforcement Learning (RL)

DEFT: Dexterous Fine-Tuning for Real-World Hand Policies

1 code implementation30 Oct 2023 Aditya Kannan, Kenneth Shaw, Shikhar Bahl, Pragna Mannam, Deepak Pathak

In this paper, we investigate these challenges, especially in the case of soft, deformable objects as well as complex, relatively long-horizon tasks.

Residual Reinforcement Learning for Robot Control

no code implementations7 Dec 2018 Tobias Johannink, Shikhar Bahl, Ashvin Nair, Jianlan Luo, Avinash Kumar, Matthias Loskyll, Juan Aparicio Ojea, Eugen Solowjow, Sergey Levine

In this paper, we study how we can solve difficult control problems in the real world by decomposing them into a part that is solved efficiently by conventional feedback control methods, and the residual which is solved with RL.

Friction reinforcement-learning +1

Neural Dynamic Policies for End-to-End Sensorimotor Learning

no code implementations NeurIPS 2020 Shikhar Bahl, Mustafa Mukadam, Abhinav Gupta, Deepak Pathak

We show that NDPs outperform the prior state-of-the-art in terms of either efficiency or performance across several robotic control tasks for both imitation and reinforcement learning setups.

Imitation Learning reinforcement-learning +1

Hierarchical Neural Dynamic Policies

no code implementations12 Jul 2021 Shikhar Bahl, Abhinav Gupta, Deepak Pathak

We tackle the problem of generalization to unseen configurations for dynamic tasks in the real world while learning from high-dimensional image input.

Human-to-Robot Imitation in the Wild

no code implementations19 Jul 2022 Shikhar Bahl, Abhinav Gupta, Deepak Pathak

We approach the problem of learning by watching humans in the wild.

VideoDex: Learning Dexterity from Internet Videos

no code implementations8 Dec 2022 Kenneth Shaw, Shikhar Bahl, Deepak Pathak

We build a learning algorithm, VideoDex, that leverages visual, action, and physical priors from human video datasets to guide robot behavior.

ALAN: Autonomously Exploring Robotic Agents in the Real World

no code implementations13 Feb 2023 Russell Mendonca, Shikhar Bahl, Deepak Pathak

Robotic agents that operate autonomously in the real world need to continuously explore their environment and learn from the data collected, with minimal human supervision.

Affordances from Human Videos as a Versatile Representation for Robotics

no code implementations CVPR 2023 Shikhar Bahl, Russell Mendonca, Lili Chen, Unnat Jain, Deepak Pathak

Utilizing internet videos of human behavior, we train a visual affordance model that estimates where and how in the scene a human is likely to interact.

Imitation Learning

Structured World Models from Human Videos

no code implementations21 Aug 2023 Russell Mendonca, Shikhar Bahl, Deepak Pathak

We propose an approach for robots to efficiently learn manipulation skills using only a handful of real-world interaction trajectories from many different settings.

Efficient RL via Disentangled Environment and Agent Representations

no code implementations5 Sep 2023 Kevin Gmelin, Shikhar Bahl, Russell Mendonca, Deepak Pathak

Agents that are aware of the separation between themselves and their environments can leverage this understanding to form effective representations of visual input.

PlayFusion: Skill Acquisition via Diffusion from Language-Annotated Play

no code implementations7 Dec 2023 Lili Chen, Shikhar Bahl, Deepak Pathak

To make diffusion models more useful for skill learning, we encourage robotic agents to acquire a vocabulary of skills by introducing discrete bottlenecks into the conditional behavior generation process.

Denoising

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