Yijie Zhang

If there is no underfitting, there is no Cold Posterior Effect

Scaling up q-learning via exploiting state–action equivalence

Opponent learning awareness and modelling in multi-objective normal form games

Deep coherent exploration for continuous control

On the inconsistency of Bayesian inference for misspecified neural networks

Opponent Modelling for Reinforcement Learning in Multi-Objective Normal Form Games.

A utility-based analysis of equilibria in multi-objective normal-form games

Opponent modelling using policy reconstruction for multi-objective normal form games