Chelsea Finn

is this you? claim profile

∙ 0 followers
Google ∙ berkeley college ∙ Stanford University

Research Scientist at Google Brain, Post-doctoral scholar at UC Berkeley

Online Meta-Learning

A central capability of intelligent systems is the ability to continuous...
02/22/2019 ∙ by Chelsea Finn, et al. ∙ 54 ∙ share

read it
Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning

Meta-reinforcement learning algorithms can enable robots to acquire new ...
10/24/2019 ∙ by Tianhe Yu, et al. ∙ 45 ∙ share

read it
Entity Abstraction in Visual Model-Based Reinforcement Learning

This paper tests the hypothesis that modeling a scene in terms of entiti...
10/28/2019 ∙ by Rishi Veerapaneni, et al. ∙ 33 ∙ share

read it
RoboNet: Large-Scale Multi-Robot Learning

Robot learning has emerged as a promising tool for taming the complexity...
10/24/2019 ∙ by Sudeep Dasari, et al. ∙ 33 ∙ share

read it
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables

Deep reinforcement learning algorithms require large amounts of experien...
03/19/2019 ∙ by Kate Rakelly, et al. ∙ 32 ∙ share

read it
NoRML: No-Reward Meta Learning

Efficiently adapting to new environments and changes in dynamics is crit...
03/04/2019 ∙ by Yuxiang Yang, et al. ∙ 28 ∙ share

read it
Model-Based Reinforcement Learning for Atari

Model-free reinforcement learning (RL) can be used to learn effective po...
03/01/2019 ∙ by Łukasz Kaiser, et al. ∙ 20 ∙ share

read it
Meta-Learning without Memorization

The ability to learn new concepts with small amounts of data is a critic...
12/09/2019 ∙ by Mingzhang Yin, et al. ∙ 19 ∙ share

read it
Continuous Meta-Learning without Tasks

Meta-learning is a promising strategy for learning to efficiently learn ...
12/18/2019 ∙ by James Harrison, et al. ∙ 15 ∙ share

read it
Gradient Surgery for Multi-Task Learning

While deep learning and deep reinforcement learning (RL) systems have de...
01/19/2020 ∙ by Tianhe Yu, et al. ∙ 15 ∙ share

read it
Reasoning About Physical Interactions with Object-Oriented Prediction and Planning

Object-based factorizations provide a useful level of abstraction for in...
12/28/2018 ∙ by Michael Janner, et al. ∙ 14 ∙ share

read it
One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks

We consider the problem of learning multi-stage vision-based tasks on a ...
10/25/2018 ∙ by Tianhe Yu, et al. ∙ 12 ∙ share

read it
Learning Predictive Models From Observation and Interaction

Learning predictive models from interaction with the world allows an age...
12/30/2019 ∙ by Karl Schmeckpeper, et al. ∙ 12 ∙ share

read it
Language as an Abstraction for Hierarchical Deep Reinforcement Learning

Solving complex, temporally-extended tasks is a long-standing problem in...
06/18/2019 ∙ by Yiding Jiang, et al. ∙ 9 ∙ share

read it
Guided Meta-Policy Search

Reinforcement learning (RL) algorithms have demonstrated promising resul...
04/01/2019 ∙ by Russell Mendonca, et al. ∙ 8 ∙ share

read it
End-to-End Robotic Reinforcement Learning without Reward Engineering

The combination of deep neural network models and reinforcement learning...
04/16/2019 ∙ by Avi Singh, et al. ∙ 8 ∙ share

read it
SMiRL: Surprise Minimizing RL in Dynamic Environments

All living organisms struggle against the forces of nature to carve out ...
12/11/2019 ∙ by Glen Berseth, et al. ∙ 8 ∙ share

read it
Unsupervised Curricula for Visual Meta-Reinforcement Learning

In principle, meta-reinforcement learning algorithms leverage experience...
12/09/2019 ∙ by Allan Jabri, et al. ∙ 7 ∙ share

read it
Unsupervised Visuomotor Control through Distributional Planning Networks

While reinforcement learning (RL) has the potential to enable robots to ...
02/14/2019 ∙ by Tianhe Yu, et al. ∙ 6 ∙ share

read it
VideoFlow: A Flow-Based Generative Model for Video

Generative models that can model and predict sequences of future events ...
03/04/2019 ∙ by Manoj Kumar, et al. ∙ 6 ∙ share

read it
Meta-Inverse Reinforcement Learning with Probabilistic Context Variables

Providing a suitable reward function to reinforcement learning can be di...
09/20/2019 ∙ by Lantao Yu, et al. ∙ 6 ∙ share

read it
Unsupervised Learning via Meta-Learning

A central goal of unsupervised learning is to acquire representations fr...
10/04/2018 ∙ by Kyle Hsu, et al. ∙ 4 ∙ share

read it
Time Reversal as Self-Supervision

A longstanding challenge in robot learning for manipulation tasks has be...
10/02/2018 ∙ by Suraj Nair, et al. ∙ 4 ∙ share

read it
Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL

Humans and animals can learn complex predictive models that allow them t...
12/18/2018 ∙ by Anusha Nagabandi, et al. ∙ 4 ∙ share

read it
Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation

Video prediction models combined with planning algorithms have shown pro...
09/12/2019 ∙ by Suraj Nair, et al. ∙ 4 ∙ share

read it
Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning

Prediction is an appealing objective for self-supervised learning of beh...
10/06/2018 ∙ by Frederik Ebert, et al. ∙ 2 ∙ share

read it
Manipulation by Feel: Touch-Based Control with Deep Predictive Models

Touch sensing is widely acknowledged to be important for dexterous robot...
03/11/2019 ∙ by Stephen Tian, et al. ∙ 2 ∙ share

read it
Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight

Machine learning techniques have enabled robots to learn narrow, yet com...
04/11/2019 ∙ by Annie Xie, et al. ∙ 2 ∙ share

read it
Meta-Learning with Implicit Gradients

A core capability of intelligent systems is the ability to quickly learn...
09/10/2019 ∙ by Aravind Rajeswaran, et al. ∙ 2 ∙ share

read it
Training an Interactive Helper

Developing agents that can quickly adapt their behavior to new tasks rem...
06/24/2019 ∙ by Mark Woodward, et al. ∙ 1 ∙ share

read it
Watch, Try, Learn: Meta-Learning from Demonstrations and Reward

Imitation learning allows agents to learn complex behaviors from demonst...
06/07/2019 ∙ by Allan Zhou, et al. ∙ 1 ∙ share

read it
Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm

Learning to learn is a powerful paradigm for enabling models to learn fr...
10/31/2017 ∙ by Chelsea Finn, et al. ∙ 0 ∙ share

read it
One-Shot Visual Imitation Learning via Meta-Learning

In order for a robot to be a generalist that can perform a wide range of...
09/14/2017 ∙ by Chelsea Finn, et al. ∙ 0 ∙ share

read it
Generalizing Skills with Semi-Supervised Reinforcement Learning

Deep reinforcement learning (RL) can acquire complex behaviors from low-...
12/01/2016 ∙ by Chelsea Finn, et al. ∙ 0 ∙ share

read it
A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models

Generative adversarial networks (GANs) are a recently proposed class of ...
11/11/2016 ∙ by Chelsea Finn, et al. ∙ 0 ∙ share

read it
Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization

Reinforcement learning can acquire complex behaviors from high-level spe...
03/01/2016 ∙ by Chelsea Finn, et al. ∙ 0 ∙ share

read it
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

We propose an algorithm for meta-learning that is model-agnostic, in the...
03/09/2017 ∙ by Chelsea Finn, et al. ∙ 0 ∙ share

read it
Deep Visual Foresight for Planning Robot Motion

A key challenge in scaling up robot learning to many skills and environm...
10/03/2016 ∙ by Chelsea Finn, et al. ∙ 0 ∙ share

read it
Unsupervised Learning for Physical Interaction through Video Prediction

A core challenge for an agent learning to interact with the world is to ...
05/23/2016 ∙ by Chelsea Finn, et al. ∙ 0 ∙ share

read it
End-to-End Training of Deep Visuomotor Policies

Policy search methods can allow robots to learn control policies for a w...
04/02/2015 ∙ by Sergey Levine, et al. ∙ 0 ∙ share

read it
Learning Compact Convolutional Neural Networks with Nested Dropout

Recently, nested dropout was proposed as a method for ordering represent...
12/22/2014 ∙ by Chelsea Finn, et al. ∙ 0 ∙ share

read it
Self-Supervised Visual Planning with Temporal Skip Connections

In order to autonomously learn wide repertoires of complex skills, robot...
10/15/2017 ∙ by Frederik Ebert, et al. ∙ 0 ∙ share

read it
Stochastic Variational Video Prediction

Predicting the future in real-world settings, particularly from raw sens...
10/30/2017 ∙ by Mohammad Babaeizadeh, et al. ∙ 0 ∙ share

read it
Recasting Gradient-Based Meta-Learning as Hierarchical Bayes

Meta-learning allows an intelligent agent to leverage prior learning epi...
01/26/2018 ∙ by Erin Grant, et al. ∙ 0 ∙ share

read it
Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods

In this paper, we explore deep reinforcement learning algorithms for vis...
02/28/2018 ∙ by Deirdre Quillen, et al. ∙ 0 ∙ share

read it
Universal Planning Networks

A key challenge in complex visuomotor control is learning abstract repre...
04/02/2018 ∙ by Aravind Srinivas, et al. ∙ 0 ∙ share

read it
Learning to Adapt: Meta-Learning for Model-Based Control

Although reinforcement learning methods can achieve impressive results i...
03/30/2018 ∙ by Ignasi Clavera, et al. ∙ 0 ∙ share

read it
One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning

Humans and animals are capable of learning a new behavior by observing o...
02/05/2018 ∙ by Tianhe Yu, et al. ∙ 0 ∙ share

read it
Stochastic Adversarial Video Prediction

Being able to predict what may happen in the future requires an in-depth...
04/04/2018 ∙ by Alex X. Lee, et al. ∙ 0 ∙ share

read it
Learning a Prior over Intent via Meta-Inverse Reinforcement Learning

A significant challenge for the practical application of reinforcement l...
05/31/2018 ∙ by Kelvin Xu, et al. ∙ 0 ∙ share

read it

Chelsea Finn

Featured Co-authors