Satinder Singh

Multistage Attack Graph Security Games: Heuristic Strategies, with Empirical Game-Theoretic Analysis

2018 · Security and Communication Networks

We study the problem of allocating limited security countermeasures to protect network data from cyber-attacks, for scenarios modeled by Bayesian attack graphs. We consider multistage interactions between a network administrator and cybercriminals, formulated as a …

Learning End-to-End Goal-Oriented Dialog with Multiple Answers

2018 · arXiv (Cornell University)

In a dialog, there can be multiple valid next utterances at any point. The present end-to-end neural methods for dialog do not take this into account. They learn with the assumption that at any time …

Discovering Diverse Nearly Optimal Policies withSuccessor Features.

2021 · arXiv (Cornell University)

Finding different solutions to the same problem is a key aspect of intelligence associated with creativity and adaptation to novel situations. In reinforcement learning, a set of diverse policies can be useful for exploration, transfer, …

Adaptive Pairwise Weights for Temporal Credit Assignment

2022 · Proceedings of the AAAI Conference on Artificial Intelligence

How much credit (or blame) should an action taken in a state get for a future reward? This is the fundamental temporal credit assignment problem in Reinforcement Learning (RL). One of the earliest and still …