87 citations · 170 across the 26 of their papers we have counts for
33 papers
Hierarchical Behaviour Spaces
Michael Tryfan Matthews, Anssi Kanervisto, Jakob Foerster +3
Recent work in hierarchical reinforcement learning has shown success in scaling to billions of timesteps when learning over a set of predefined option reward functions. We show tha…
BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning
Yitang Li, Zhengyi Luo, Tonghe Zhang +10
Building Behavioral Foundation Models (BFMs) for humanoid robots has the potential to unify diverse control tasks under a single, promptable generalist policy. However, existing ap…
Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models
Andrea Tirinzoni, Ahmed Touati, Jesse Farebrother +5
Unsupervised reinforcement learning (RL) aims at pre-training agents that can solve a wide range of downstream tasks in complex environments. Despite recent advancements, existing…
Fast Adaptation with Behavioral Foundation Models
Harshit Sikchi, Andrea Tirinzoni, Ahmed Touati +6
Unsupervised zero-shot reinforcement learning (RL) has emerged as a powerful paradigm for pretraining behavioral foundation models (BFMs), enabling agents to solve a wide range of…
Diffusion for World Modeling: Visual Details Matter in Atari
Eloi Alonso, Adam Jelley, Vincent Micheli +4
World models constitute a promising approach for training reinforcement learning agents in a safe and sample-efficient manner. Recent world models predominantly operate on sequence…
Toward Human-AI Alignment in Large-Scale Multi-Player Games
Sugandha Sharma, Guy Davidson, Khimya Khetarpal +4
Achieving human-AI alignment in complex multi-agent games is crucial for creating trustworthy AI agents that enhance gameplay. We propose a method to evaluate this alignment using…
BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks
Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas +3
The MineRL BASALT competition has served to catalyze advances in learning from human feedback through four hard-to-specify tasks in Minecraft, such as create and photograph a water…
Visual Encoders for Data-Efficient Imitation Learning in Modern Video Games
Lukas Schäfer, Logan Jones, Anssi Kanervisto +7
Video games have served as useful benchmarks for the decision-making community, but going beyond Atari games towards modern games has been prohibitively expensive for the vast majo…
Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition
Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas +27
To facilitate research in the direction of fine-tuning foundation models from human feedback, we held the MineRL BASALT Competition on Fine-Tuning from Human Feedback at NeurIPS 20…
Imitating Human Behaviour with Diffusion Models
Tim Pearce, Tabish Rashid, Anssi Kanervisto +8
Diffusion models have emerged as powerful generative models in the text-to-image domain. This paper studies their application as observation-to-action models for imitating human be…
A2C is a special case of PPO
Shengyi Huang, Anssi Kanervisto, Antonin Raffin +3
Advantage Actor-critic (A2C) and Proximal Policy Optimization (PPO) are popular deep reinforcement learning algorithms used for game AI in recent years. A common understanding is t…
GAN-Aimbots: Using Machine Learning for Cheating in First Person Shooters
Anssi Kanervisto, Tomi Kinnunen, Ville Hautamäki
Playing games with cheaters is not fun, and in a multi-billion-dollar video game industry with hundreds of millions of players, game developers aim to improve the security and, con…
Insights From the NeurIPS 2021 NetHack Challenge
Eric Hambro, Sharada Mohanty, Dmitrii Babaev +26
In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge. Participants were tasked with developing a program or agent that can win (i.e., 'ascend' i…
MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned
Anssi Kanervisto, Stephanie Milani, Karolis Ramanauskas +19
Reinforcement learning competitions advance the field by providing appropriate scope and support to develop solutions toward a specific problem. To promote the development of more…
Optimizing Tandem Speaker Verification and Anti-Spoofing Systems
Anssi Kanervisto, Ville Hautamäki, Tomi Kinnunen +1
As automatic speaker verification (ASV) systems are vulnerable to spoofing attacks, they are typically used in conjunction with spoofing countermeasure (CM) systems to improve secu…
Agents that Listen: High-Throughput Reinforcement Learning with Multiple Sensory Systems
Shashank Hegde, Anssi Kanervisto, Aleksei Petrenko
Humans and other intelligent animals evolved highly sophisticated perception systems that combine multiple sensory modalities. On the other hand, state-of-the-art artificial agents…
The MineRL BASALT Competition on Learning from Human Feedback
Rohin Shah, Cody Wild, Steven H. Wang +10
The last decade has seen a significant increase of interest in deep learning research, with many public successes that have demonstrated its potential. As such, these systems are n…
Distilling Reinforcement Learning Tricks for Video Games
Anssi Kanervisto, Christian Scheller, Yanick Schraner +1
Reinforcement learning (RL) research focuses on general solutions that can be applied across different domains. This results in methods that RL practitioners can use in almost any…
Towards robust and domain agnostic reinforcement learning competitions
William Hebgen Guss, Stephanie Milani, Nicholay Topin +26
Reinforcement learning competitions have formed the basis for standard research benchmarks, galvanized advances in the state-of-the-art, and shaped the direction of the field. Desp…
Multi-task Learning with Attention for End-to-end Autonomous Driving
Keishi Ishihara, Anssi Kanervisto, Jun Miura +1
Autonomous driving systems need to handle complex scenarios such as lane following, avoiding collisions, taking turns, and responding to traffic signals. In recent years, approache…
Back to Square One: Superhuman Performance in Chutes and Ladders Through Deep Neural Networks and Tree Search
Dylan Ashley, Anssi Kanervisto, Brendan Bennett
We present AlphaChute: a state-of-the-art algorithm that achieves superhuman performance in the ancient game of Chutes and Ladders. We prove that our algorithm converges to the Nas…
General Characterization of Agents by States they Visit
Anssi Kanervisto, Tomi Kinnunen, Ville Hautamäki
Behavioural characterizations (BCs) of decision-making agents, or their policies, are used to study outcomes of training algorithms and as part of the algorithms themselves to enco…
Action Space Shaping in Deep Reinforcement Learning
Anssi Kanervisto, Christian Scheller, Ville Hautamäki
Reinforcement learning (RL) has been successful in training agents in various learning environments, including video-games. However, such work modifies and shrinks the action space…
Benchmarking End-to-End Behavioural Cloning on Video Games
Anssi Kanervisto, Joonas Pussinen, Ville Hautamäki
Behavioural cloning, where a computer is taught to perform a task based on demonstrations, has been successfully applied to various video games and robotics tasks, with and without…