Alert button
Picture for Alan Fern

Alan Fern

Alert button

Structured Attention Graphs for Understanding Deep Image Classifications

Dec 08, 2020
Vivswan Shitole, Li Fuxin, Minsuk Kahng, Prasad Tadepalli, Alan Fern

Figure 1 for Structured Attention Graphs for Understanding Deep Image Classifications
Figure 2 for Structured Attention Graphs for Understanding Deep Image Classifications
Figure 3 for Structured Attention Graphs for Understanding Deep Image Classifications
Figure 4 for Structured Attention Graphs for Understanding Deep Image Classifications
Viaarxiv icon

Learning Task Space Actions for Bipedal Locomotion

Nov 09, 2020
Helei Duan, Jeremy Dao, Kevin Green, Taylor Apgar, Alan Fern, Jonathan Hurst

Figure 1 for Learning Task Space Actions for Bipedal Locomotion
Figure 2 for Learning Task Space Actions for Bipedal Locomotion
Figure 3 for Learning Task Space Actions for Bipedal Locomotion
Figure 4 for Learning Task Space Actions for Bipedal Locomotion
Viaarxiv icon

Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition

Nov 02, 2020
Jonah Siekmann, Yesh Godse, Alan Fern, Jonathan Hurst

Figure 1 for Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition
Figure 2 for Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition
Figure 3 for Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition
Figure 4 for Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition
Viaarxiv icon

Learning Spring Mass Locomotion: Guiding Policies with a Reduced-Order Model

Oct 21, 2020
Kevin Green, Yesh Godse, Jeremy Dao, Ross L. Hatton, Alan Fern, Jonathan Hurst

Figure 1 for Learning Spring Mass Locomotion: Guiding Policies with a Reduced-Order Model
Figure 2 for Learning Spring Mass Locomotion: Guiding Policies with a Reduced-Order Model
Figure 3 for Learning Spring Mass Locomotion: Guiding Policies with a Reduced-Order Model
Figure 4 for Learning Spring Mass Locomotion: Guiding Policies with a Reduced-Order Model
Viaarxiv icon

Dream and Search to Control: Latent Space Planning for Continuous Control

Oct 19, 2020
Anurag Koul, Varun V. Kumar, Alan Fern, Somdeb Majumdar

Figure 1 for Dream and Search to Control: Latent Space Planning for Continuous Control
Figure 2 for Dream and Search to Control: Latent Space Planning for Continuous Control
Figure 3 for Dream and Search to Control: Latent Space Planning for Continuous Control
Figure 4 for Dream and Search to Control: Latent Space Planning for Continuous Control
Viaarxiv icon

DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs

Oct 18, 2020
Aayam Shrestha, Stefan Lee, Prasad Tadepalli, Alan Fern

Figure 1 for DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs
Figure 2 for DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs
Figure 3 for DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs
Figure 4 for DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs
Viaarxiv icon

Contrastive Explanations for Reinforcement Learning via Embedded Self Predictions

Oct 11, 2020
Zhengxian Lin, Kim-Ho Lam, Alan Fern

Figure 1 for Contrastive Explanations for Reinforcement Learning via Embedded Self Predictions
Figure 2 for Contrastive Explanations for Reinforcement Learning via Embedded Self Predictions
Figure 3 for Contrastive Explanations for Reinforcement Learning via Embedded Self Predictions
Figure 4 for Contrastive Explanations for Reinforcement Learning via Embedded Self Predictions
Viaarxiv icon

Understanding Finite-State Representations of Recurrent Policy Networks

Jun 06, 2020
Mohamad H. Danesh, Anurag Koul, Alan Fern, Saeed Khorram

Figure 1 for Understanding Finite-State Representations of Recurrent Policy Networks
Figure 2 for Understanding Finite-State Representations of Recurrent Policy Networks
Figure 3 for Understanding Finite-State Representations of Recurrent Policy Networks
Figure 4 for Understanding Finite-State Representations of Recurrent Policy Networks
Viaarxiv icon

Learning Memory-Based Control for Human-Scale Bipedal Locomotion

Jun 03, 2020
Jonah Siekmann, Srikar Valluri, Jeremy Dao, Lorenzo Bermillo, Helei Duan, Alan Fern, Jonathan Hurst

Figure 1 for Learning Memory-Based Control for Human-Scale Bipedal Locomotion
Figure 2 for Learning Memory-Based Control for Human-Scale Bipedal Locomotion
Figure 3 for Learning Memory-Based Control for Human-Scale Bipedal Locomotion
Figure 4 for Learning Memory-Based Control for Human-Scale Bipedal Locomotion
Viaarxiv icon