4 papers
On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners
David Mguni, Julian Ma, Jun Wang
Large Language Models (LLMs) are frequently portrayed as general-purpose solvers capable of solving arbitrary tasks. We argue that this view overlooks a fundamental constraint: lan…
On the Geometry of Games and their Solvers
Yaqi Sun, Julian Ma, David Mguni
A central challenge in game theory and learning systems such as GANs is understanding which algorithms can efficiently compute equilibria across the heterogeneous landscape of game…
Fault Tolerant Multi-Agent Learning with Adversarial Budget Constraints
David Mguni, Yaqi Sun, Haojun Chen +4
We study robustness to agent malfunctions in cooperative multi-agent reinforcement learning (MARL), a failure mode that is critical in practice yet underexplored in existing theory…
Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning
Lukas Schäfer, Oliver Slumbers, Stephen McAleer +3
Multi-agent reinforcement learning (MARL) requires agents to explore within a vast joint action space to find joint actions that lead to coordination. Existing value-based MARL alg…