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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Anssi Kanervisto

Agents that Listen: High-Throughput Reinforcement Learning with Multiple Sensory Systems


Jul 05, 2021
Shashank Hegde, Anssi Kanervisto, Aleksei Petrenko

* To appear in IEEE Conference on Games 2021. Video demonstrations and experiment can be found at https://sites.google.com/view/sound-rl 

  Access Paper or Ask Questions

The MineRL BASALT Competition on Learning from Human Feedback


Jul 05, 2021
Rohin Shah, Cody Wild, Steven H. Wang, Neel Alex, Brandon Houghton, William Guss, Sharada Mohanty, Anssi Kanervisto, Stephanie Milani, Nicholay Topin, Pieter Abbeel, Stuart Russell, Anca Dragan

* NeurIPS 2021 Competition Track 

  Access Paper or Ask Questions

Distilling Reinforcement Learning Tricks for Video Games


Jul 01, 2021
Anssi Kanervisto, Christian Scheller, Yanick Schraner, Ville HautamÀki

* To appear in IEEE Conference on Games 2021. Experiment code is available at https://github.com/Miffyli/rl-human-prior-tricks 

  Access Paper or Ask Questions

Towards robust and domain agnostic reinforcement learning competitions


Jun 07, 2021
William Hebgen Guss, Stephanie Milani, Nicholay Topin, Brandon Houghton, Sharada Mohanty, Andrew Melnik, Augustin Harter, Benoit Buschmaas, Bjarne Jaster, Christoph Berganski, Dennis Heitkamp, Marko Henning, Helge Ritter, Chengjie Wu, Xiaotian Hao, Yiming Lu, Hangyu Mao, Yihuan Mao, Chao Wang, Michal Opanowicz, Anssi Kanervisto, Yanick Schraner, Christian Scheller, Xiren Zhou, Lu Liu, Daichi Nishio, Toi Tsuneda, Karolis Ramanauskas, Gabija Juceviciute

* 20 pages, several figures, published PMLR 

  Access Paper or Ask Questions

Multi-task Learning with Attention for End-to-end Autonomous Driving


Apr 21, 2021
Keishi Ishihara, Anssi Kanervisto, Jun Miura, Ville HautamÀki

* Accepted to CVPR 2021 Workshop on Autonomous Driving 

  Access Paper or Ask Questions

Back to Square One: Superhuman Performance in Chutes and Ladders Through Deep Neural Networks and Tree Search


Apr 01, 2021
Dylan Ashley, Anssi Kanervisto, Brendan Bennett


  Access Paper or Ask Questions

Policy Supervectors: General Characterization of Agents by their Behaviour


Dec 02, 2020
Anssi Kanervisto, Tomi Kinnunen, Ville HautamÀki

* Code available at https://github.com/Miffyli/policy-supervectors 

  Access Paper or Ask Questions

Playing Minecraft with Behavioural Cloning


May 07, 2020
Anssi Kanervisto, Janne Karttunen, Ville HautamÀki

* To appear in Post Proceedings of the Competitions & Demonstrations Track @ NeurIPS2019. Source code available at https://github.com/Miffyli/minecraft-bc 

  Access Paper or Ask Questions

Benchmarking End-to-End Behavioural Cloning on Video Games


Apr 02, 2020
Anssi Kanervisto, Joonas Pussinen, Ville HautamÀki


  Access Paper or Ask Questions

Action Space Shaping in Deep Reinforcement Learning


Apr 02, 2020
Anssi Kanervisto, Christian Scheller, Ville HautamÀki


  Access Paper or Ask Questions

An initial investigation on optimizing tandem speaker verification and countermeasure systems using reinforcement learning


Feb 06, 2020
Anssi Kanervisto, Ville HautamÀki, Tomi Kinnunen, Junichi Yamagishi

* Code available at https://github.com/Miffyli/asv-cm-reinforce 

  Access Paper or Ask Questions

Towards Debugging Deep Neural Networks by Generating Speech Utterances


Jul 06, 2019
Bilal Soomro, Anssi Kanervisto, Trung Ngo Trong, Ville HautamÀki

* Accepted to Interspeech 2019 

  Access Paper or Ask Questions

Do Autonomous Agents Benefit from Hearing?


May 10, 2019
Abraham Woubie, Anssi Kanervisto, Janne Karttunen, Ville Hautamaki


  Access Paper or Ask Questions

From Video Game to Real Robot: The Transfer between Action Spaces


May 02, 2019
Janne Karttunen, Anssi Kanervisto, Ville HautamÀki, Ville Kyrki

* Two first authors contributed equally 

  Access Paper or Ask Questions

ToriLLE: Learning Environment for Hand-to-Hand Combat


Jul 26, 2018
Anssi Kanervisto, Ville HautamÀki

* https://github.com/Miffyli/ToriLLE 

  Access Paper or Ask Questions

Image-to-Markup Generation with Coarse-to-Fine Attention


Jun 13, 2017
Yuntian Deng, Anssi Kanervisto, Jeffrey Ling, Alexander M. Rush

* Accepted by ICML 2017 

  Access Paper or Ask Questions