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

Add to Chrome

Add to Firefox

Picture for Jimmy Ba

Jimmy Ba

Exploring Model-based Planning with Policy Networks

Jun 20, 2019
Tingwu Wang, Jimmy Ba

Figure 1 for Exploring Model-based Planning with Policy Networks

Figure 2 for Exploring Model-based Planning with Policy Networks

Figure 3 for Exploring Model-based Planning with Policy Networks

Figure 4 for Exploring Model-based Planning with Policy Networks

* 8 pages, 7 figures

Access Paper or Ask Questions

Neural Graph Evolution: Towards Efficient Automatic Robot Design

Jun 12, 2019
Tingwu Wang, Yuhao Zhou, Sanja Fidler, Jimmy Ba

Figure 1 for Neural Graph Evolution: Towards Efficient Automatic Robot Design

Figure 2 for Neural Graph Evolution: Towards Efficient Automatic Robot Design

Figure 3 for Neural Graph Evolution: Towards Efficient Automatic Robot Design

Figure 4 for Neural Graph Evolution: Towards Efficient Automatic Robot Design

* ICLR 2019

Access Paper or Ask Questions

DOM-Q-NET: Grounded RL on Structured Language

Feb 19, 2019
Sheng Jia, Jamie Kiros, Jimmy Ba

Figure 1 for DOM-Q-NET: Grounded RL on Structured Language

Figure 2 for DOM-Q-NET: Grounded RL on Structured Language

Figure 3 for DOM-Q-NET: Grounded RL on Structured Language

Figure 4 for DOM-Q-NET: Grounded RL on Structured Language

* International Conference on Learning Representations (ICLR), 2019

Access Paper or Ask Questions

Reversible Recurrent Neural Networks

Oct 25, 2018
Matthew MacKay, Paul Vicol, Jimmy Ba, Roger Grosse

Figure 1 for Reversible Recurrent Neural Networks

Figure 2 for Reversible Recurrent Neural Networks

Figure 3 for Reversible Recurrent Neural Networks

Figure 4 for Reversible Recurrent Neural Networks

* Published as a conference paper at NIPS 2018

Access Paper or Ask Questions

On the Convergence and Robustness of Training GANs with Regularized Optimal Transport

May 22, 2018
Maziar Sanjabi, Jimmy Ba, Meisam Razaviyayn, Jason D. Lee

Figure 1 for On the Convergence and Robustness of Training GANs with Regularized Optimal Transport

Figure 2 for On the Convergence and Robustness of Training GANs with Regularized Optimal Transport

Figure 3 for On the Convergence and Robustness of Training GANs with Regularized Optimal Transport

Figure 4 for On the Convergence and Robustness of Training GANs with Regularized Optimal Transport

Access Paper or Ask Questions

Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches

Apr 02, 2018
Yeming Wen, Paul Vicol, Jimmy Ba, Dustin Tran, Roger Grosse

Figure 1 for Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches

Figure 2 for Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches

Figure 3 for Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches

Figure 4 for Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches

* Published as a conference paper at ICLR 2018

Access Paper or Ask Questions

Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation

Aug 18, 2017
Yuhuai Wu, Elman Mansimov, Shun Liao, Roger Grosse, Jimmy Ba

Figure 1 for Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation

Figure 2 for Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation

Figure 3 for Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation

Figure 4 for Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation

* 14 pages, 9 figures; update github repo link

Access Paper or Ask Questions