47 citations · 201 across the 15 of their papers we have counts for
17 papers
Use-Case-Grounded Simulations for Explanation Evaluation
Valerie Chen, Nari Johnson, Nicholay Topin +2
A growing body of research runs human subject evaluations to study whether providing users with explanations of machine learning models can help them with practical real-world use…
MAVIPER: Learning Decision Tree Policies for Interpretable Multi-Agent Reinforcement Learning
Stephanie Milani, Zhicheng Zhang, Nicholay Topin +4
Many recent breakthroughs in multi-agent reinforcement learning (MARL) require the use of deep neural networks, which are challenging for human experts to interpret and understand.…
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…
A Survey of Explainable Reinforcement Learning
Stephanie Milani, Nicholay Topin, Manuela Veloso +1
Explainable reinforcement learning (XRL) is an emerging subfield of explainable machine learning that has attracted considerable attention in recent years. The goal of XRL is to el…
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…
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…
Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methods
Nicholay Topin, Stephanie Milani, Fei Fang +1
Current work in explainable reinforcement learning generally produces policies in the form of a decision tree over the state space. Such policies can be used for formal safety veri…
The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors
William H. Guss, Mario Ynocente Castro, Sam Devlin +12
Although deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples, affording only a shrink…
Guaranteeing Reproducibility in Deep Learning Competitions
Brandon Houghton, Stephanie Milani, Nicholay Topin +5
To encourage the development of methods with reproducible and robust training behavior, we propose a challenge paradigm where competitors are evaluated directly on the performance…
Retrospective Analysis of the 2019 MineRL Competition on Sample Efficient Reinforcement Learning
Stephanie Milani, Nicholay Topin, Brandon Houghton +5
To facilitate research in the direction of sample efficient reinforcement learning, we held the MineRL Competition on Sample Efficient Reinforcement Learning Using Human Priors at…
MineRL: A Large-Scale Dataset of Minecraft Demonstrations
William H. Guss, Brandon Houghton, Nicholay Topin +4
The sample inefficiency of standard deep reinforcement learning methods precludes their application to many real-world problems. Methods which leverage human demonstrations require…
Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy
Aaron M. Roth, Nicholay Topin, Pooyan Jamshidi +1
There is a growing desire in the field of reinforcement learning (and machine learning in general) to move from black-box models toward more "interpretable AI." We improve interpre…
Generation of Policy-Level Explanations for Reinforcement Learning
Nicholay Topin, Manuela Veloso
Though reinforcement learning has greatly benefited from the incorporation of neural networks, the inability to verify the correctness of such systems limits their use. Current wor…
The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors
William H. Guss, Cayden Codel, Katja Hofmann +9
Though deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples. As state-of-the-art reinf…
Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates
Leslie N. Smith, Nicholay Topin
In this paper, we describe a phenomenon, which we named "super-convergence", where neural networks can be trained an order of magnitude faster than with standard training methods.…
Exploring loss function topology with cyclical learning rates
Leslie N. Smith, Nicholay Topin
We present observations and discussion of previously unreported phenomena discovered while training residual networks. The goal of this work is to better understand the nature of n…
Deep Convolutional Neural Network Design Patterns
Leslie N. Smith, Nicholay Topin
Recent research in the deep learning field has produced a plethora of new architectures. At the same time, a growing number of groups are applying deep learning to new applications…