A. Kanervisto

发表

Stable-Baselines3: Reliable Reinforcement Learning Implementations

A. Gleave, Anssi Kanervisto, Ashley Hill, 2021, J. Mach. Learn. Res..

Imitating Human Behaviour with Diffusion Models

Sergio Valcarcel Macua, I. Momennejad, David Bignell, 2023, ICLR.

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

Alexander M. Rush, Jeffrey Ling, Anssi Kanervisto, 2016, ICML.

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

Jun Miura, Ville Hautamäki, Anssi Kanervisto, 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

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

Shashank Hegde, Anssi Kanervisto, Aleksei Petrenko, 2021, 2021 IEEE Conference on Games (CoG).

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

Alexander M. Rush, Yuntian Deng, Jeffrey Ling, 2016, ICML.

Do Autonomous Agents Benefit from Hearing? pdf

Abraham Woubie, Ville Hautamäki, Anssi Kanervisto, 2019, ArXiv.

Action Space Shaping in Deep Reinforcement Learning

Ville Hautamäki, Anssi Kanervisto, Christian Scheller, 2020, 2020 IEEE Conference on Games (CoG).

What You Get Is What You See: A Visual Markup Decompiler pdf

Alexander M. Rush, Anssi Kanervisto, Yuntian Deng, 2016, ArXiv.

Benchmarking End-to-End Behavioural Cloning on Video Games

Ville Hautamäki, Anssi Kanervisto, Joonas Pussinen, 2020, 2020 IEEE Conference on Games (CoG).

Insights From the NeurIPS 2021 NetHack Challenge

Edward Grefenstette, Nantas Nardelli, Jack Parker-Holder, 2022, NeurIPS.

MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned

Anssi Kanervisto, A. Shpilman, Deheng Ye, 2022, NeurIPS.

Policy Supervectors: General Characterization of Agents by their Behaviour pdf

Tomi Kinnunen, Ville Hautamäki, Anssi Kanervisto, 2020, ArXiv.

General Characterization of Agents by States they Visit

T. Kinnunen, Anssi Kanervisto, Ville Hautamaki, 2020, 2012.01244.

ToriLLE: Learning Environment for Hand-to-Hand Combat

Ville Hautamäki, Anssi Kanervisto, Ville Hautamäki, 2018, 2019 IEEE Conference on Games (CoG).

Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition

João F. Henriques, Vinicius G. Goecks, Nicholas R. Waytowich, 2023, NeurIPS.

The MineRL BASALT Competition on Learning from Human Feedback pdf

Pieter Abbeel, Stuart J. Russell, Rohin Shah, 2021, ArXiv.

Playing Minecraft with Behavioural Cloning

Ville Hautamäki, Anssi Kanervisto, Janne Karttunen, 2020, NeurIPS.

GAN-Aimbots: Using Machine Learning for Cheating in First Person Shooters

T. Kinnunen, Ville Hautamäki, A. Kanervisto, 2022, IEEE Transactions on Games.

Distilling Reinforcement Learning Tricks for Video Games

Ville Hautamäki, Anssi Kanervisto, Yanick Schraner, 2021, 2021 IEEE Conference on Games (CoG).

Towards robust and domain agnostic reinforcement learning competitions

William H. Guss, H. Ritter, S. Mohanty, 2021, NeurIPS.

Augmenting Microsurgical Training: Microsurgical Instrument Detection Using Convolutional Neural Networks

Roman Bednarik, Piotr Bartczak, Hana Vrzakova, 2018, 2018 IEEE 31st International Symposium on Computer-Based Medical Systems (CBMS).

Visual Encoders for Data-Efficient Imitation Learning in Modern Video Games

David Bignell, Tabish Rashid, Raluca Georgescu, 2023, ArXiv.

Optimizing Tandem Speaker Verification and Anti-Spoofing Systems

Tomi Kinnunen, Junichi Yamagishi, Ville Hautamäki, 2022, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

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

J. Yamagishi, T. Kinnunen, Ville Hautamäki, 2020, Odyssey.

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

Anssi Kanervisto, Brendan Bennett, Dylan R. Ashley, 2021, ArXiv.

Toward Human-AI Alignment in Large-Scale Multi-Player Games

I. Momennejad, Khimya Khetarpal, A. Kanervisto, 2024, ArXiv.

Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents

Diego Perez Liebana, William H. Guss, Alec Radford, 2022 .