Rosa Del Mar

Issue 2 2026-01-02

Rosa Del Mar

Daily Brief

Issue 2 2026-01-02

Depth Scaling In Self-Supervised Rl Is Real But Recipe-Dependent

  • The work is described as challenging the conventional wisdom that reinforcement learning is not scalable by demonstrating continued gains at extreme depth.
  • The reported gains depend on using a different self-supervised objective and are not presented as simply dropping larger networks into standard RL algorithms like PPO or SAC.
  • A proposed future direction is distilling or pruning very deep teacher policies into shallower student models to reduce inference cost while retaining performance.

Forecasting-Pipeline-And-Physical-Limits

  • Operational systems now achieve useful forecast skill out to roughly 10–15 days.
  • Consumer and ambient sensors (e.g., doorbell cameras, car sensors, phone sensors) and social media posts could serve as supplementary weather observations, but their data quality is uncertain.
  • DeepMind’s AI weather forecasting approach uses supervised learning to map an estimated current state to a future state and iteratively feeds predictions back as inputs to generate multi-step forecasts.

Alternative Portfolio Frameworks And Products

  • The forward-cap portfolio concept invests based on estimated future market capitalizations rather than today’s market-cap weights.
  • In macroeconomics, “investment” primarily refers to firm spending for future production rather than households buying securities.
  • A bond ladder concentrated in the 0–5 year maturity range can produce a more systematic and certain outcome than exposure to 30-year Treasuries.