Policy Gradient Steering: Interventions from Behavioral Objectives Paper • 2607.27574 • Published Jul 30
Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning Paper • 2502.00726 • Published Feb 2, 2025 • 1
Contrastive Sparse Autoencoders for Interpreting Planning of Chess-Playing Agents Paper • 2406.04028 • Published Jun 6, 2024 • 2
