Outcome-based Reinforcement Learning to Predict the Future

2025-05-23

AI Summary

研究通过改进强化学习方法（GRPO和ReMax），解决现实预测任务中奖励信号延迟、噪声大的问题，使14B模型在预测准确性和校准性上超越前沿基线。

Technology Category

• Machine Learning: Reinforcement Learning
• Search and Optimization: Learning to Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Reinforcement learning with verifiable rewards (RLVR) has boosted math and coding in large language models, yet there has been little effort to extend RLVR into messier, real-world domains like forecasting. One sticking point is that outcome-based reinforcement learning for forecasting must learn from binary, delayed, and noisy rewards, a regime where standard fine-tuning is brittle. We show that outcome-only online RL on a 14B model can match frontier-scale accuracy and surpass it in calibration and hypothetical prediction market betting by adapting two leading algorithms, Group-Relative Policy Optimisation (GRPO) and ReMax, to the forecasting setting. Our adaptations remove per-question variance scaling in GRPO, apply baseline-subtracted advantages in ReMax, hydrate training with 100k temporally consistent synthetic questions, and introduce lightweight guard-rails that penalise gibberish, non-English responses and missing rationales, enabling a single stable pass over 110k events. Scaling ReMax to 110k questions and ensembling seven predictions yields a 14B model that matches frontier baseline o1 on accuracy on our holdout set (Brier = 0.193, p = 0.23) while beating it in calibration (ECE = 0.042, p<0.001). A simple trading rule turns this calibration edge into $127 of hypothetical profit versus $92 for o1 (p = 0.037). This demonstrates that refined RLVR methods can convert small-scale LLMs into potentially economically valuable forecasting tools, with implications for scaling this to larger models.

Problem

• Extends RLVR to real-world forecasting with noisy rewards
• Adapts GRPO and ReMax for outcome-based forecasting tasks
• Enhances small LLMs into economically valuable forecasting tools

Innovation

• Adapt GRPO and ReMax for forecasting
• Use synthetic questions for training
• Implement guard-rails for response quality