Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count% of corpus
0.3%0.5%0.8%0.1% · Aug 201919922001200920172026
2 results for “multi-timestep”
Multi-timestep models for Model-based Reinforcement Learningcs.LG

The paper improves model-based reinforcement learning by using multi-timestep objectives.

problem Compounding errors in one-step dynamics models as trajectory length increases.
method Developed a multi-timestep objective as a weighted sum of losses at various future horizons.
result Exponentially decaying weights significantly improve long-horizon performance.
model-based reinforcement learningmulti-timestepone-step dynamicstrajectory lengthreinforcement learning
2023-10-09abs ↗pdf ↗