标签:reinforcement learning

EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Neuroevolution

EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Neuroevolution William McNally  Kanav Vats  Alexander Wong  John McPheeSystems De……

EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Neuroevolution

EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Neuroevolution William McNally  Kanav Vats  Alexander Wong  John McPheeSystems De……

A Framework for Learning Predator-prey Agents from Simulation to Real World.

A Framework for Learning Predator-prey Agents from Simulation to Real World. Jiunhan Chen, Department of Computer Science, Vrije Universiteit Amsterdam, the Netherlands &em……

Recurrent Neural Networks for video object detection

Recurrent Neural Networks for video object detection Bin Qasim Ahmad Technical University of MunichDepartment of InformaticsMunich, Germanyahmad.qasim@tum.de  Pettirsch……

WaveTransform: Crafting Adversarial Examples via Input Decomposition

WaveTransform: Crafting Adversarial Examples via Input Decomposition Divyam Anshumaan1IIIT-Delhi, India, 2Texas A&M University, Kingsville, USA, 3IIT Jodhpur, India &ems……

Causal variables from reinforcement learning using generalized Bellman equations

Causal variables from reinforcement learning using generalized Bellman equations Tue Herlau /newtoggle notes/toggletruenotes/togglefalsenotes/newtogglearxiv/toggletruearxiv ……

On the Transfer of Disentangled Representations in Realistic Settings

On the Transfer of Disentangled Representations in Realistic Settings /nameAndrea Dittadi /affnum1Equal contribution. Correspondence to: <adit@dtu.dk>, <frederik.traeub……

COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning

COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning Avi Singh, Albert Yu, Jonathan Yang, Jesse Zhang, Aviral Kumar, Sergey LevineUniversity of Cali……

Track-Assignment Detailed Routing Using Attention-based Policy Model With Supervision

Track-Assignment Detailed Routing Using Attention-based Policy Model With Supervision Haiguang Liaohaiguanl@andrew.cmu.eduCarnegie Mellon UnversityPittsburghPA15213, Qingyi ……

Eye Tracking Data Collection Protocol for VR for Remotely Located Subjects using Blockchain and Smart Contracts

Eye Tracking Data Collection Protocol for VR for Remotely Located Subjects using Blockchain and Smart Contracts Efe Bozkir, Shahram Eivazi, Mete Akgün and Enkelejda Kasneci ……