Publications (11)
On the Complexity of Reconnaissance Blind Chess
Jared Markowitz, Ryan W. Gardner, Ashley J. Llorens
This paper provides a complexity analysis for the game of reconnaissance blind chess (RBC), a recently-introduced variant of chess where each player does not know the positions of…
Trojans in Artificial Intelligence (TrojAI) Final Report
Kristopher W. Reese, Taylor Kulp-McDowall, Michael Majurski +68
The Intelligence Advanced Research Projects Activity (IARPA) launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI T…
Learning a Group-Aware Policy for Robot Navigation
Kapil Katyal, Yuxiang Gao, Jared Markowitz +4
Human-aware robot navigation promises a range of applications in which mobile robots bring versatile assistance to people in common human environments. While prior research has mos…
Handling Cost and Constraints with Off-Policy Deep Reinforcement Learning
Jared Markowitz, Jesse Silverberg, Gary Collins
By reusing data throughout training, off-policy deep reinforcement learning algorithms offer improved sample efficiency relative to on-policy approaches. For continuous action spac…
Triangular Dropout: Variable Network Width without Retraining
Edward W. Staley, Jared Markowitz
One of the most fundamental design choices in neural networks is layer width: it affects the capacity of what a network can learn and determines the complexity of the solution. Thi…
Combining Deep Universal Features, Semantic Attributes, and Hierarchical Classification for Zero-Shot Learning
Jared Markowitz, Aurora C. Schmidt, Philippe M. Burlina +1
We address zero-shot (ZS) learning, building upon prior work in hierarchical classification by combining it with approaches based on semantic attribute estimation. For both non-nov…
Discovering strategies for coastal resilience with AI-based prediction and optimization
Jared Markowitz, Alexander New, Jennifer Sleeman +5
Tropical storms cause extensive property damage and loss of life, making them one of the most destructive types of natural hazards. The development of predictive models that identi…
A Risk-Sensitive Approach to Policy Optimization
Jared Markowitz, Ryan W. Gardner, Ashley Llorens +2
Standard deep reinforcement learning (DRL) aims to maximize expected reward, considering collected experiences equally in formulating a policy. This differs from human decision-mak…
Clipped-Objective Policy Gradients for Pessimistic Policy Optimization
Jared Markowitz, Edward W. Staley
To facilitate efficient learning, policy gradient approaches to deep reinforcement learning (RL) are typically paired with variance reduction measures and strategies for making lar…
Addressing Visual Search in Open and Closed Set Settings
Nathan Drenkow, Philippe Burlina, Neil Fendley +2
Searching for small objects in large images is a task that is both challenging for current deep learning systems and important in numerous real-world applications, such as remote s…
Meta Arcade: A Configurable Environment Suite for Meta-Learning
Edward W. Staley, Chace Ashcraft, Benjamin Stoler +4
Most approaches to deep reinforcement learning (DRL) attempt to solve a single task at a time. As a result, most existing research benchmarks consist of individual games or suites…