Aya Shabbar

Aya Shabbar

Research Assistant

Publications

You can also find my articles on my Google Scholar profile.

Idea: Online Opponent Modeling with Foundation Models

Published in ICML, 2024

This paper proposes using foundation models (FMs), i.e., large language models (LLMs) and vision-language models (VLMs), to achieve this goal. The LLM generates instructions that help the agent to learn features of the behavior of the opponent and ultimately enables the agent to exploit the opponent’s strategy in the current environment d(s0).

Recommended citation: Aya, Shabbar. (2024). "Idea: Online Opponent Modeling with Foundation Models." ICML. 1(3).
Download Paper

Reward-Free Reinforcement Learning with GNN and Adversarial Linear Mixture MDPs

Published in European Workshop on Reinforcement Learning, 2024

This paper proposes a new framework for the reward-free RL setting with function approximation i.e. the adversarial linear mixture MDPs. As Jin, et al. (2020).

Recommended citation: Shabbar, Aya. (2024). "Reward-Free Reinforcement Learning with GNN and Adversarial Linear Mixture MDPs." European Workshop on Reinforcement Learning. 1(3).
Download Paper

Generative Adversarial Skill Estimation in Opponent Modeling

Published in RL Conference, 2024

In this paper, I propose a novel method called generative adversarial skill estimation (GASE) to encourage the estimation and the probability of success in RL opponent modeling via introducing an intrinsic reward output from a foundation model generative adversarial network, where the generator provides fake samples of the opponent’s actions that help discriminator to identify those failed actions with their probability of success.

Recommended citation: Aya, Shabbar. (2024). "Generative Adversarial Skill Estimation in Opponent Modeling." RL Conference. 1(2).
Download Paper

Generative-Discriminative Mean Field Distribution Approximation in Multi-agent Reinforcement Learning

Published in RL Conference, 2024

This research aims to propose a model-based reinforcement learning algorithm, GD-MFRL that efficiently represents the distribution using function approximation in a two-part generative and discriminative setting; (i) one part learns to generate distributions by trial and error, and (ii) the other part tries to evaluate these distributions.

Recommended citation: Aya, Shabbar. (2024). " Generative-Discriminative Mean Field Distribution Approximation in Multi-agent Reinforcement Learning." RL Conference. 1(1).
Download Paper