Outcome-based Reinforcement Learning to Predict the Future

• URL: http://arxiv.org/abs/2505.17989v3
• Date: Wed, 30 Jul 2025 05:18:39 GMT
• Title: Outcome-based Reinforcement Learning to Predict the Future
• Authors: Benjamin Turtel, Danny Franklin, Kris Skotheim, Luke Hewitt, Philipp Schoenegger,
• Abstract summary: We show that a compact (14B) reasoning model can be trained to match or surpass the predictive accuracy of frontier models like o1.<n>The model's performance is also practically meaningful: in a Polymarket trading simulation, we estimate that its bets would have yielded a return on investment of over 10%.
• Score: 1.4313866885019229
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has been an effective approach for improving Large Language Models' reasoning in domains such as coding and mathematics. Here, we apply RLVR methods towards forecasting future real-world events - a challenging task for RL due to the very noisy (and delayed) outcomes involved. Using a novel dataset of recent questions from a prediction market, and accompanying relevant news headlines, we show that a compact (14B) reasoning model can be trained to match or surpass the predictive accuracy of frontier models like o1, while greatly improving probabilistic calibration. The model's performance is also practically meaningful: in a Polymarket trading simulation, we estimate that its bets would have yielded a return on investment of over 10% across all questions in the test set. We detail and compare approaches used in training our model, including augmenting our training-data with synthetic prediction questions, guardrails for learning stability, and median prediction sampling at inference-time.

Related papers

• Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining [74.83412846804977]
  Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models.<n>We present a systematic end-to-end study of RL fine-tuning for mathematical reasoning by training models entirely from scratch.
  arXiv  Detail & Related papers  (2025-04-10T17:15:53Z)
• Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification [50.717692060500696]
  Next-token prediction with the logarithmic loss is a cornerstone of autoregressive sequence modeling.<n>Next-token prediction can be made robust so as to achieve $C=tilde O(H)$, representing moderate error amplification.<n>No computationally efficient algorithm can achieve sub-polynomial approximation factor $C=e(log H)1-Omega(1)$.
  arXiv  Detail & Related papers  (2025-02-18T02:52:00Z)
• Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training [51.41246396610475]
  This paper aims to predict performance in closed-book question answering (QA) without the help of external tools.<n>We conduct large-scale retrieval and semantic analysis across the pre-training corpora of 21 publicly available and 3 custom-trained large language models.<n>Building on these foundations, we propose Size-dependent Mutual Information (SMI), an information-theoretic metric that linearly correlates pre-training data characteristics.
  arXiv  Detail & Related papers  (2025-02-06T13:23:53Z)
• Minimal Batch Adaptive Learning Policy Engine for Real-Time Mid-Price Forecasting in High-Frequency Trading [1.7802147489386628]
  We present a novel approach to mid-price forecasting using Level 1 limit order book (LOB) data from NASDAQ.<n>We introduce the Adaptive Learning Policy Engine (ALPE) - a reinforcement learning (RL)-based agent designed for batch-free, immediate mid-price forecasting.
  arXiv  Detail & Related papers  (2024-12-26T22:49:53Z)
• Future-Guided Learning: A Predictive Approach To Enhance Time-Series Forecasting [4.866362841501992]
  We introduce Future-Guided Learning, an approach that enhances time-series event forecasting through a dynamic feedback mechanism inspired by predictive coding.<n>Our method involves two models: a detection model that analyzes future data to identify critical events and a forecasting model that predicts these events based on current data.<n>We validate our approach on a variety of tasks, demonstrating a 44.8% increase in AUC-ROC for seizure prediction using EEG data, and a 48.7% reduction in MSE for forecasting in nonlinear dynamical systems.
  arXiv  Detail & Related papers  (2024-10-19T21:22:55Z)
• ReAugment: Model Zoo-Guided RL for Few-Shot Time Series Augmentation and Forecasting [74.00765474305288]
  We present a pilot study on using reinforcement learning (RL) for time series data augmentation.<n>Our method, ReAugment, tackles three critical questions: which parts of the training set should be augmented, how the augmentation should be performed, and what advantages RL brings to the process.
  arXiv  Detail & Related papers  (2024-09-10T07:34:19Z)
• Language models scale reliably with over-training and on downstream tasks [121.69867718185125]
  Scaling laws are useful guides for derisking expensive training runs. However, there remain gaps between current studies and how language models are trained. In contrast, scaling laws mostly predict loss on inference, but models are usually compared on downstream task performance.
  arXiv  Detail & Related papers  (2024-03-13T13:54:00Z)
• Prediction of rare events in the operation of household equipment using co-evolving time series [1.1249583407496218]
  Our approach involves a weighted autologistic regression model, where we leverage the temporal behavior of the data to enhance predictive capabilities. Evaluation on synthetic and real-world datasets confirms that our approach outperform state-of-the-art of predicting home equipment failure methods.
  arXiv  Detail & Related papers  (2023-12-15T00:21:00Z)
• Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback [91.22679548111127]
  A trustworthy real-world prediction system should produce well-calibrated confidence scores. We show that verbalized confidences emitted as output tokens are typically better-calibrated than the model's conditional probabilities.
  arXiv  Detail & Related papers  (2023-05-24T10:12:33Z)
• Learning Sample Difficulty from Pre-trained Models for Reliable Prediction [55.77136037458667]
  We propose to utilize large-scale pre-trained models to guide downstream model training with sample difficulty-aware entropy regularization. We simultaneously improve accuracy and uncertainty calibration across challenging benchmarks.
  arXiv  Detail & Related papers  (2023-04-20T07:29:23Z)
• nanoLM: an Affordable LLM Pre-training Benchmark via Accurate Loss Prediction across Scales [65.01417261415833]
  We present an approach to predict the pre-training loss based on our observations that Maximal Update Parametrization (muP) enables accurate fitting of scaling laws. With around 14% of the one-time pre-training cost, we can accurately forecast the loss for models up to 52B. Our goal with nanoLM is to empower researchers with limited resources to reach meaningful conclusions on large models.
  arXiv  Detail & Related papers  (2023-04-14T00:45:01Z)
• Feature Selection with Annealing for Forecasting Financial Time Series [2.44755919161855]
  This study provides a comprehensive method for forecasting financial time series based on tactical input output feature mapping techniques using machine learning (ML) models. Experiments indicate that the FSA algorithm increased the performance of ML models, regardless of problem type.
  arXiv  Detail & Related papers  (2023-03-03T21:33:38Z)
• Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future [73.03458424369657]
  In real-time forecasting in public health, data collection is a non-trivial and demanding task. 'Backfill' phenomenon and its effect on model performance has been barely studied in the prior literature. We formulate a novel problem and neural framework Back2Future that aims to refine a given model's predictions in real-time.
  arXiv  Detail & Related papers  (2021-06-08T14:48:20Z)
• Robust Validation: Confident Predictions Even When Distributions Shift [19.327409270934474]
  We describe procedures for robust predictive inference, where a model provides uncertainty estimates on its predictions rather than point predictions. We present a method that produces prediction sets (almost exactly) giving the right coverage level for any test distribution in an $f$-divergence ball around the training population. An essential component of our methodology is to estimate the amount of expected future data shift and build robustness to it.
  arXiv  Detail & Related papers  (2020-08-10T17:09:16Z)
• Using Machine Learning to Forecast Future Earnings [2.476455202580687]
  We have evaluated the feasibility and suitability of adopting the Machine Learning Models on the forecast of corporation fundamentals. Our model has already been proved to be capable of serving as a favorable auxiliary tool for analysts to conduct better predictions on company fundamentals.
  arXiv  Detail & Related papers  (2020-05-26T16:39:38Z)
• A Locally Adaptive Interpretable Regression [7.4267694612331905]
  Linear regression is one of the most interpretable prediction models. In this work, we introduce a locally adaptive interpretable regression (LoAIR) Our model achieves comparable or better predictive performance than the other state-of-the-art baselines.
  arXiv  Detail & Related papers  (2020-05-07T09:26:14Z)
• A Time Series Analysis-Based Stock Price Prediction Using Machine Learning and Deep Learning Models [0.0]
  We present a very robust and accurate framework of stock price prediction that consists of an agglomeration of statistical, machine learning and deep learning models. We use the daily stock price data, collected at five minutes interval of time, of a very well known company that is listed in the National Stock Exchange (NSE) of India. We contend that the agglomerative approach of model building that uses a combination of statistical, machine learning, and deep learning approaches, can very effectively learn from the volatile and random movement patterns in a stock price data.
  arXiv  Detail & Related papers  (2020-04-17T19:41:22Z)
• Understanding and Mitigating the Tradeoff Between Robustness and Accuracy [88.51943635427709]
  Adversarial training augments the training set with perturbations to improve the robust error. We show that the standard error could increase even when the augmented perturbations have noiseless observations from the optimal linear predictor.
  arXiv  Detail & Related papers  (2020-02-25T08:03:01Z)
• Value-driven Hindsight Modelling [68.658900923595]
  Value estimation is a critical component of the reinforcement learning (RL) paradigm. Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function. We develop an approach for representation learning in RL that sits in between these two extremes. This provides tractable prediction targets that are directly relevant for a task, and can thus accelerate learning the value function.
  arXiv  Detail & Related papers  (2020-02-19T18:10:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.