Search Results for author:
Found 28 papers, 18 papers with code
Toward Human-AI Alignment in Large-Scale Multi-Player Games
First, we analyze extensive human gameplay data from Xbox's Bleeding Edge (100K+ games), uncovering behavioral patterns in a complex task space.
BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks
Given the completion of two years of BASALT competitions, we offer to the community a formalized benchmark through the BASALT Evaluation and Demonstrations Dataset (BEDD), which serves as a resource for algorithm development and performance assessment.
Visual Encoders for Data-Efficient Imitation Learning in Modern Video Games
Video games have served as useful benchmarks for the decision making community, but going beyond Atari games towards training agents in modern games has been prohibitively expensive for the vast majority of the research community.
Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition
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 2022.
Imitating Human Behaviour with Diffusion Models
This paper studies their application as observation-to-action models for imitating human behaviour in sequential environments.
A2C is a special case of PPO
Advantage Actor-critic (A2C) and Proximal Policy Optimization (PPO) are popular deep reinforcement learning algorithms used for game AI in recent years.
GAN-Aimbots: Using Machine Learning for Cheating in First Person Shooters
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, consequently, the user experience of their games by preventing cheating.
Retrospective on the 2021 BASALT Competition on Learning from Human Feedback
The goal of the competition was to promote research towards agents that use learning from human feedback (LfHF) techniques to solve open-world tasks.
Insights From the NeurIPS 2021 NetHack Challenge
In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge.
MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned
With this in mind, we hosted the third edition of the MineRL ObtainDiamond competition, MineRL Diamond 2021, with a separate track in which we permitted any solution to promote the participation of newcomers.
Optimizing Tandem Speaker Verification and Anti-Spoofing Systems
As automatic speaker verification (ASV) systems are vulnerable to spoofing attacks, they are typically used in conjunction with spoofing countermeasure (CM) systems to improve security.
Agents that Listen: High-Throughput Reinforcement Learning with Multiple Sensory Systems
We are currently in the process of merging the augmented simulator with the main ViZDoom code repository.
The MineRL BASALT Competition on Learning from Human Feedback
Rather than training AI systems using a predefined reward function or using a labeled dataset with a predefined set of categories, we instead train the AI system using a learning signal derived from some form of human feedback, which can evolve over time as the understanding of the task changes, or as the capabilities of the AI system improve.
Distilling Reinforcement Learning Tricks for Video Games
Reinforcement learning (RL) research focuses on general solutions that can be applied across different domains.
Towards robust and domain agnostic reinforcement learning competitions
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.
Multi-task Learning with Attention for End-to-end Autonomous Driving
This does not only improve the success rate of standard benchmarks, but also the ability to react to traffic lights, which we show with standard benchmarks.
Back to Square One: Superhuman Performance in Chutes and Ladders Through Deep Neural Networks and Tree Search
We present AlphaChute: a state-of-the-art algorithm that achieves superhuman performance in the ancient game of Chutes and Ladders.
General Characterization of Agents by States they Visit
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 encourage unique policies, match expert policy or restrict changes to policy per update.
Playing Minecraft with Behavioural Cloning
MineRL 2019 competition challenged participants to train sample-efficient agents to play Minecraft, by using a dataset of human gameplay and a limit number of steps the environment.
Benchmarking End-to-End Behavioural Cloning on Video Games
We take a step towards a general approach and study the general applicability of behavioural cloning on twelve video games, including six modern video games (published after 2010), by using human demonstrations as training data.
Action Space Shaping in Deep Reinforcement Learning
In this work, we aim to gain insight on these action space modifications by conducting extensive experiments in video-game environments.
An initial investigation on optimizing tandem speaker verification and countermeasure systems using reinforcement learning
The spoofing countermeasure (CM) systems in automatic speaker verification (ASV) are not typically used in isolation of each other.
Towards Debugging Deep Neural Networks by Generating Speech Utterances
One such debugging method used with image classification DNNs is activation maximization, which generates example-images that are classified as one of the classes.
Do Autonomous Agents Benefit from Hearing?
In this work, we propose the use of audio as complementary information to visual only in state representation.
From Video Game to Real Robot: The Transfer between Action Spaces
Deep reinforcement learning has proven to be successful for learning tasks in simulated environments, but applying same techniques for robots in real-world domain is more challenging, as they require hours of training.
Who Do I Sound Like? Showcasing Speaker Recognition Technology by YouTube Voice Search
The popularization of science can often be disregarded by scientists as it may be challenging to put highly sophisticated research into words that general public can understand.
Audio and Speech Processing Sound
ToriLLE: Learning Environment for Hand-to-Hand Combat
We present Toribash Learning Environment (ToriLLE), a learning environment for machine learning agents based on the video game Toribash.
Image-to-Markup Generation with Coarse-to-Fine Attention
We present a neural encoder-decoder model to convert images into presentational markup based on a scalable coarse-to-fine attention mechanism.
