Optimization
Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem
The joint decisions of the agents influence both individual rewards and the transition of the environment. MARL in general is occupied with leading the multi-agent system to a favorable outcome. Through the lens of game theory, the notion of a "favorable outcome" is formally defined through concepts like a Nash
Efficient Model-Free Exploration in Low-Rank MDPs
What are the right computational primitives for exploration?
Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees Dohyeong Kim
However, the nonlinearity of risk measures makes it challenging to achieve convergence and optimality.
Unraveling the Gradient Descent Dynamics of Transformers
By analyzing the loss landscape of a single Transformer layer using Softmax and Gaussian attention kernels, our work provides concrete answers to these questions.
