activity
20182025
most citedDIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation

539 citations · 669 across the 16 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG20224 cited

Investigating Compounding Prediction Errors in Learned Dynamics Models

Nathan Lambert, Kristofer Pister, Roberto Calandra

Accurately predicting the consequences of agents' actions is a key prerequisite for planning in robotic control. Model-based reinforcement learning (MBRL) is one paradigm which rel…

cs.LG202133 cited

On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning

Baohe Zhang, Raghu Rajan, Luis Pineda +5

Model-based Reinforcement Learning (MBRL) is a promising framework for learning control in a data-efficient manner. MBRL algorithms can be fairly complex due to the separate dynami…

cs.LG2021

Model-Invariant State Abstractions for Model-Based Reinforcement Learning

Manan Tomar, Amy Zhang, Roberto Calandra +2

Accuracy and generalization of dynamics models is key to the success of model-based reinforcement learning (MBRL). As the complexity of tasks increases, so does the sample ineffici…

cs.LG2020

Learning Accurate Long-term Dynamics for Model-based Reinforcement Learning

Nathan O. Lambert, Albert Wilcox, Howard Zhang +2

Accurately predicting the dynamics of robotic systems is crucial for model-based control and reinforcement learning. The most common way to estimate dynamics is by fitting a one-st…

cs.LG2020

Learning Invariant Representations for Reinforcement Learning without Reconstruction

Amy Zhang, Rowan McAllister, Roberto Calandra +2

We study how representation learning can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstructio…

cs.LG20206 cited

Plan2Vec: Unsupervised Representation Learning by Latent Plans

Ge Yang, Amy Zhang, Ari S. Morcos +3

In this paper we introduce plan2vec, an unsupervised representation learning approach that is inspired by reinforcement learning. Plan2vec constructs a weighted graph on an image d…