UAlberta RLAI Talk: Viewing Reinforcement Learning Through a Physics Perspective
MarlosCMachado · x · 2026-08-11
The University of Alberta hosts annual RLAI Tea Time Talks. Marlos C. Machado shared a recording of his talk from last year, which he also presented at the RLC'25 IBRL Workshop.
The presentation explores how some of their research work in reinforcement learning can be interpreted from a physics perspective, aiming to make these academic concepts broadly accessible.
More from Research
- Beyond Slow SAEs: 4 Faster Methods for LLM Interpretability — furongh · 2026-08-11
- Why AI Text Watermarking Struggles to Meet the EU AI Act's Upcoming Mandates — deedydas · 2026-08-11
- NuclearBench: Testing if LLMs Would Launch Nukes Given the Choice — o_t_i_s_ · 2026-08-11
- Study: LLMs and Human Brains Converge on Shared Linguistic Representations — maier_ak · 2026-08-11
- Associative Memory Failure Isn't Synapse Degradation: 131k Neuron Study Reveals Identity Drift — theawkwardbong · 2026-08-11
- Ouroboros: Self-Developing Coding Agent Tops Multiple Benchmarks — Anton Razzhigaev · 2026-08-11