Giovanni Montana

Action-Free Offline-To-Online RL via Discretised State Policies

Action Dimension Coordination via Centralised Critics for Continuous Control

Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations

Retrosynthesis Planning via Worst-path Policy Optimisation in Tree-structured MDPs

Learning on One Mode: Addressing Multi-modality in Offline Reinforcement Learning

Efficient Verified Unlearning For Distillation