23.6k citations
- University of California, BerkeleyUS252 papers
- California Institute of TechnologyUS24 papers
- Lawrence Berkeley National LaboratoryUS16 papers
- University of ChicagoUS14 papers
- UCLA HealthUS13 papers
- Google (United States)US12 papers
- Moscow Institute of Thermal TechnologyRU11 papers
- University of MichiganUS11 papers
- Carnegie Mellon UniversityUS10 papers
- Centre National de la Recherche ScientifiqueFR10 papers
- Michigan Science CenterUS10 papers
- Stanford UniversityUS10 papers
11 papers · 2 filters
APS: Active Pretraining with Successor Features
Hao Liu, Pieter Abbeel
We introduce a new unsupervised pretraining objective for reinforcement learning. During the unsupervised reward-free pretraining phase, the agent maximizes mutual information betw…
Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment
Michael Chang, Sidhant Kaushik, Sergey Levine +1
Many transfer problems require re-using previously optimal decisions for solving new tasks, which suggests the need for learning algorithms that can modify the mechanisms for choos…
MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning
Kevin Li, Abhishek Gupta, Ashwin Reddy +4
Exploration in reinforcement learning is a challenging problem: in the worst case, the agent must search for high-reward states that could be hidden anywhere in the state space. Ca…
Conservative Objective Models for Effective Offline Model-Based Optimization
Brandon Trabucco, Aviral Kumar, Xinyang Geng +1
Computational design problems arise in a number of settings, from synthetic biology to computer architectures. In this paper, we aim to solve data-driven model-based optimization (…
RMA: Rapid Motor Adaptation for Legged Robots
Ashish Kumar, Zipeng Fu, Deepak Pathak +1
Successful real-world deployment of legged robots would require them to adapt in real-time to unseen scenarios like changing terrains, changing payloads, wear and tear. This paper…
Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
John Miller, Rohan Taori, Aditi Raghunathan +6
For machine learning systems to be reliable, we must understand their performance in unseen, out-of-distribution environments. In this paper, we empirically show that out-of-distri…