Beyazit Yalcinkaya — accepted AI-conference papers

2026

Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning

Beyazit Yalcinkaya, Marcell Vazquez-Chanlatte, Ameesh Shah, Hanna Krasowski, Sanjit Seshia

ICML 2026poster

We study learning multi-task, multi-agent policies for cooperative, temporal objectives, under centralized training, decentralized execution. In this setting, using automata to represent tasks assigned to agents enables breaking down a team-level objective into simpler, smaller sub-tasks. However, e…

Cited by 0 Source ↗Scholar ↗

2024

Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning

Beyazit Yalcinkaya, Niklas Lauffer, Marcell Vazquez-Chanlatte, Sanjit A. Seshia

NeurIPS 2024poster

Goal-conditioned reinforcement learning is a powerful way to control an AI agent's behavior at runtime. That said, popular goal representations, e.g., target states or natural language, are either limited to Markovian tasks or rely on ambiguous task semantics. We propose representing temporal goals…

Cited by 2 Source ↗PDF ↗Scholar ↗