Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Pieter Abbeel

Pieter Abbeel

Parameter Space Noise for Exploration

Jan 31, 2018
Matthias Plappert, Rein Houthooft, Prafulla Dhariwal, Szymon Sidor, Richard Y. Chen, Xi Chen, Tamim Asfour, Pieter Abbeel, Marcin Andrychowicz

Figure 1 for Parameter Space Noise for Exploration

Figure 2 for Parameter Space Noise for Exploration

Figure 3 for Parameter Space Noise for Exploration

Figure 4 for Parameter Space Noise for Exploration

* Updated to camera-ready ICLR submission

Access Paper or Ask Questions

PixelSNAIL: An Improved Autoregressive Generative Model

Dec 28, 2017
Xi Chen, Nikhil Mishra, Mostafa Rohaninejad, Pieter Abbeel

Figure 1 for PixelSNAIL: An Improved Autoregressive Generative Model

Figure 2 for PixelSNAIL: An Improved Autoregressive Generative Model

Figure 3 for PixelSNAIL: An Improved Autoregressive Generative Model

Figure 4 for PixelSNAIL: An Improved Autoregressive Generative Model

Access Paper or Ask Questions

A Berkeley View of Systems Challenges for AI

Dec 15, 2017
Ion Stoica, Dawn Song, Raluca Ada Popa, David Patterson, Michael W. Mahoney, Randy Katz, Anthony D. Joseph, Michael Jordan, Joseph M. Hellerstein, Joseph E. Gonzalez, Ken Goldberg, Ali Ghodsi, David Culler, Pieter Abbeel

Figure 1 for A Berkeley View of Systems Challenges for AI

* Berkeley Technical Report

Access Paper or Ask Questions

#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning

Dec 05, 2017
Haoran Tang, Rein Houthooft, Davis Foote, Adam Stooke, Xi Chen, Yan Duan, John Schulman, Filip De Turck, Pieter Abbeel

Figure 1 for #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning

Figure 2 for #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning

Figure 3 for #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning

Figure 4 for #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning

* 10 pages main text + 10 pages supplementary. Published at NIPS 2017

Access Paper or Ask Questions

Inverse Reward Design

Nov 08, 2017
Dylan Hadfield-Menell, Smitha Milli, Pieter Abbeel, Stuart Russell, Anca Dragan

Figure 1 for Inverse Reward Design

Figure 2 for Inverse Reward Design

Figure 3 for Inverse Reward Design

Figure 4 for Inverse Reward Design

* Advances in Neural Information Processing Systems 30 (NIPS 2017)

Access Paper or Ask Questions

UCB Exploration via Q-Ensembles

Nov 07, 2017
Richard Y. Chen, Szymon Sidor, Pieter Abbeel, John Schulman

Figure 1 for UCB Exploration via Q-Ensembles

Figure 2 for UCB Exploration via Q-Ensembles

Figure 3 for UCB Exploration via Q-Ensembles

Figure 4 for UCB Exploration via Q-Ensembles

Access Paper or Ask Questions

Asymmetric Actor Critic for Image-Based Robot Learning

Oct 18, 2017
Lerrel Pinto, Marcin Andrychowicz, Peter Welinder, Wojciech Zaremba, Pieter Abbeel

Figure 1 for Asymmetric Actor Critic for Image-Based Robot Learning

Figure 2 for Asymmetric Actor Critic for Image-Based Robot Learning

Figure 3 for Asymmetric Actor Critic for Image-Based Robot Learning

Figure 4 for Asymmetric Actor Critic for Image-Based Robot Learning

* Videos of experiments can be found at http://www.goo.gl/b57WTs

Access Paper or Ask Questions