6th Annual Learning for Dynamics & Control conference @ Oxford

I attended the L4DC conference at Oxford’s Maths Institute, where I enjoyed reconnecting with old colleagues and friends from the Oxford Control Group. The topics covered were:

• Foundations of learning of dynamics models
• System identification
• Optimization for machine learning
• Data-driven optimization for dynamical systems
• Distributed learning over distributed systems
• Reinforcement learning for physical systems
• Safe reinforcement learning and safe adaptive control
• Statistical learning for dynamical and control systems
• Bridging model-based and learning-based dynamical and control systems
• Physics-constrained learning
• Physical learning in dynamical and control systems applications in robotics, autonomy, biology, energy systems, transportation systems, cognitive systems, neuroscience, etc.

I went along to the tutorial sessions on

• Distributionally Robust Optimization for Control
• Learning under Requirements: Supervised and Reinforcement Learning with Constraints

followed by keynotes on

• Representation-based Learning and Control for Dynamical Systems (Na Li, Harvard)
• Learning Enabled Multi-Agent Systems in Societal Systems Transformation (S. Shankar Sastry, UC Berkeley)
• Optogenetic Feedback Control of Gene Expression in Single Cells (Mary Dunlop, Boston U.)
• The state of optimal and learning control in the 2020s (Jonas Buchli, Deepmind)
• Inductive Biases for Robot Reinforcement Learning (Jan Peters, TU Darmstadt)
• Efficient & Realistic Simulation for Autonomous Driving (Shimon Whiteson, Oxford/Waymo)

Finally, the proceedings are here.