Learning to Bet for Horizon-Aware Anytime-Valid Testing

Samet Oymak, Shubhanshu Shekhar, Ege Taga

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• egetaga/learning-to-bet

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We develop horizon-aware anytime-valid tests and confidence sequences for bounded means under a strict deadline N . Using the betting/eprocess framework, we cast horizon-aware betting as a finite-horizon optimal control problem with state space (t, log W t ), where t is the time and W t is the test martingale value. We first show that in certain interior regions of the state space, policies that deviate significantly from Kelly betting are provably suboptimal, while Kelly betting reaches the threshold with high probability. We then identify sufficient conditions showing that outside this region, more aggressive betting than Kelly can be better if the bettor is behind schedule, and less aggressive can be better if the bettor is ahead. Taken together these results suggest a simple phase diagram in the (t, log W t ) plane, delineating regions where Kelly, fractional Kelly, and aggressive betting may be preferable. Guided by this phase diagram, we introduce a Deep Reinforcement Learning approach based on a universal Deep Q-Network (DQN) agent that learns a single policy from synthetic experience and maps simple statistics of past observations to bets across horizons and null values. In limited-horizon experiments, the learned DQN policy yields stateof-the-art results.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2603.19551")
get_code_for_paper("2603.19551")
have("2603.19551")

Connect an agent — have() is free.