Enhances on-policy RL with past reward statistics and hot-wiring.
problem Challenges of sparse reward signals in on-policy methods.
method Multi-critic supervision and hot-wiring mechanism.
result Improves on-policy learning for sparse reward tasks.
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “statistical reward accumulation”
Exploration Unboundcs.LG
An agent explores indefinitely in an environment with unlimited rewards.
problem Balancing exploration and exploitation in environments with unlimited rewards.
method Simple example of an environment with unbounded rewards and optimal agent behavior.
result An optimal agent always explores to maximize rewards, regardless of accumulated knowledge.
Reinforcement learning for embodied agents is a challenging problem. The accumulated reward to be optimized is often a very rugged function, and gradient methods are impaired by many local optimizers. We demonstrate, in an experimental setting, that incorporating an intrinsic reward can smoothen the optimization landsc…
Improved statistical computation through efficient matrix sampling.
problem Reducing computational cost in large-scale statistical methods.
method Accumulative sub-sampling method to improve statistical efficiency.
result Effective matrix size control improves computational efficiency.
Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While constraints may solve this issue, there is no closed form solution for general co…
New method analyzes accumulation precision in deep learning networks.
problem Lack of precision analysis for accumulation in deep learning training.
method Statistical approach to analyze partial sum accumulations and derive equations for minimum required bits.
result Reduced accumulation precision can lead to loss of information and degraded network quality.
Proposes a method to boost deep reinforcement learning with sparse rewards.
problem Challenges in learning complex behaviors with long horizons and sparse rewards.
method Predictive coding for reward shaping.
result Achieves better learning by providing reward signals that understand environment dynamics and emphasize useful features.
Several statistical and machine learning methods are proposed to estimate the type and intensity of physical load and accumulated fatigue . They are based on the statistical analysis of accumulated and moving window data subsets with construction of a kurtosis-skewness diagram. This approach was applied to the data gat…
Algorithm optimizes decision-making in unknown MDPs with minimal regret.
problem Optimizing decision-making in unknown discrete MDPs with bounded expected shortest path.
method Developed BUCRL{} algorithm achieving regret.
result First polynomial time Bayesian algorithm for unknown MDPs with high probability worst-case regret.
Improves generative models by optimizing rewards and sample editing.
problem Efficiently generating high-reward samples with structural constraints.
method Introduces MDM-VGB, a discrete diffusion sampler that augments unmasking generation with reward-guided remasking.
result MDM-VGB achieves quadratic complexity and robustness to noise, outperforming heuristics like best-of-.
Model of capital accumulation in a complex exchange space.
problem Capital accumulation dynamics in heterogeneous producer-consumer systems.
method Statistical field theory approach to analyze interactions and dynamics.
result Capital accumulation and agent position in the exchange space are correlated.
DANCE method improves large-scale learning efficiency via accumulating sample strategy.
problem Efficiently solving large-scale empirical risk minimization problems.
method Distributed Accumulated Newton Conjugate gradient (DANCE) method with multistage approach.
result The method achieves satisfactory statistical accuracy with fewer passes over data.
Improved text generation using transferable rewards from related tasks.
problem Non-differentiable task-specific scores limit the use of policy gradient methods in text generation.
method Transferable Reward Learner that uses model-based rewards for sentence-level and phrase-level similarity.
result Improved performance on semantic evaluation measures in image captioning tasks.
The paper enhances preference learning by incorporating response time data.
problem Lack of temporal information in user decision-making for reward model learning.
method Integrates response time alongside binary choice data using the EZ model and Neyman-orthogonal loss functions.
result Response time-augmented approach reduces error rates from exponential to polynomial scaling, improving sample efficiency.
The paper tackles noisy multi-armed bandit problems with improved regret guarantees.
problem Tackling noisy evaluations in multi-armed bandit problems.
method Derives different algorithmic approaches and theoretical guarantees based on the type of observation functions.
result Improved regret guarantees for noisy linear functions of true rewards.
A new exploration method for RL using parameter space noise.
problem Improving exploration in deep reinforcement learning.
method Switching isotropic and directional exploration in parameter space with parameter space noise.
result The proposed method achieves competitive results and better performance in sparse reward environments.
Study reward-free RL in non-linear settings, improving efficiency and removing assumptions.
problem Improving sample efficiency in reward-free reinforcement learning for non-linear function approximation.
method Proposed RFOLIVE algorithm for minimal structural assumptions, analyzed hardness results for reward-free and reward-aware exploration.
result Statistical efficiency and hardness results under various structural assumptions, no need for reachability or explorability assumptions.
Develops statistical framework for resolving reward function ambiguity in inverse reinforcement learning.
problem Non-uniqueness of reward functions in inverse reinforcement learning.
method Entropy regularization combined with least-squares reconstruction of the reward from the soft Bellman residual.
result Least-squares reward function is unique and consistent with the expert policy.
Study of historic stock returns distributions, highlighting asymmetry and outliers.
problem Understanding the asymmetry in accumulated gains and losses in stock returns over time.
method Analyzing decades-long historic distributions of S&P500 returns, comparing gains and losses, using statistical U-tests and fitting log-log scale linearly.
result The mean of de-trended distributions increases linearly with the number of days of accumulation, and the overall skew is negative, indicating heavier tails of losses.
Method tackles uncertainty in reward models for LLMs from heterogeneous human feedback.
problem Uncertainty in reward models for LLMs from heterogeneous human feedback.
method Heterogeneous preference framework and alternating gradient descent algorithm.
result Established theoretical guarantees for estimator convergence and asymptotic distribution.
New algorithm balances user reward and statistical inference by mixing TS with UR based on difference size.
problem Combining statistical inference with user reward in adaptive experiments.
method TS-PostDiff algorithm that uses UR when differences are small and TS when large.
result TS-PostDiff reduces false positives and increases statistical power for small differences, while maximizing reward for large ones.
Book introduces multi-armed bandits for decision-making under uncertainty.
problem Decision-making under uncertainty with limited information.
method Self-contained chapters covering various types of bandits.
result Provides a comprehensive introduction to multi-armed bandits.
The aim of the present article is to offer a strictly mathematical, statistical treatment of the current account balances in EU and in the Eurozone. Based on Eurostat data, an overview of the total and annual balances is first made for different collections among the EU countries. Then, using the Mathematica technical …
We consider a planning problem where the dynamics and rewards of the environment depend on a hidden static parameter referred to as the context. The objective is to learn a strategy that maximizes the accumulated reward across all contexts. The new model, called Contextual Markov Decision Process (CMDP), can model a cu…
Paper develops robust policy evaluation for reinforcement learning with outlier and heavy-tailed rewards.
problem Outlier contamination and heavy-tailed rewards in reinforcement learning.
method Develops a fully online robust policy evaluation procedure and efficient statistical inference.
result Establishes the Bahadur-type representation of the estimator and develops an online inference procedure.
Paper improves action selection for accurate parameter estimation in linear bandits.
problem Best action identification in stochastic linear bandits with fixed confidence constraints.
method Designs a sequential adaptive policy to estimate underlying parameter efficiently.
result The designed policy achieves the same estimation error scaling as a lower bound.
The paper models financial markets and real economy interactions using a large agent framework.
problem Understanding capital allocation and accumulation in financial markets and real economy interactions.
method Developed a field-formalism model to analyze interactions between financial markets and real economy with a large number of heterogeneous agents.
result The number of firms in each sector depends on the aggregate financial capital invested and expected long-term returns.
SQIL uses a simple reward strategy to encourage long-horizon imitation of expert demonstrations.
problem Challenges in imitation learning with high-dimensional, continuous observations and unknown dynamics.
method Imitates expert demonstrations by providing a constant reward of +1 for matching actions in demonstrated states, and 0 for all others.
result Empirically outperforms behavioral cloning and achieves competitive results compared to GAIL.
New GFlowNet training framework using policy gradients for combinatorial object generation.
problem Training efficiency and robustness in GFlowNet models.
method Policy-dependent rewards and coupled training strategy for forward and backward policies.
result Advanced RL perspectives for robust gradient estimation improve GFlowNet performance.
Algorithm improves transfer learning by inferring successor maps.
problem Machine learning challenges in multi-task scenarios.
method Combining factorized representations and nonparametric memory-based approaches.
result Improves transfer capabilities and outperforms other algorithms.
The paper analyzes the reward improvement of aligned policies in large language models.
problem Optimizing policies in large language models while staying close to a reference policy.
method Information-theoretic analysis and reduction to exponential order statistics.
result Information-theoretic upper bounds on reward improvement are derived.
The paper develops a robust algorithm for contextual bandits with heavy-tailed rewards.
problem Contextual bandits with heavy-tailed rewards.
method Develops an algorithm based on Catoni's estimator for robust statistics, applying it to contextual bandits with general function approximation.
result Establishes regret bounds that depend on cumulative reward variance and logarithmically on the reward range and number of rounds.
PILAF optimizes reward models from human feedback for better policy alignment.
problem Creating accurate reward models from human feedback for policy optimization.
method Policy-Interpolated Learning for Aligned Feedback (PILAF) that explicitly aligns preference learning with maximizing underlying oracle reward.
result PILAF is optimal from both optimization and statistical perspectives, demonstrating strong performance in RLHF settings.
This study examines deep hedging for S&P 500 options, revealing systematic delta corrections and fragility.
problem Understanding and validating deep hedging strategies for financial options.
method Compared TD3 agents with a Black-Scholes delta hedge, using walk-forward tests and symbolic regression.
result Deep hedging agents learn systematic delta corrections, which can improve performance but are regime-fragile.
Survive method improves model-based RL by avoiding terminal states, reducing sample complexity.
problem High sample complexity in model-free RL methods limits real-world applications.
method Introduces 'survival' concept to model-based RL, focusing on avoiding terminal states instead of maximizing rewards.
result Survive method reduces training effort by focusing on terminal states, improving model-based RL performance.
RNNs classify text by accumulating evidence on a low-dimensional manifold.
problem Understanding how RNNs solve text classification tasks.
method Dynamical systems analysis applied to trained RNNs.
result RNNs use a low-dimensional attractor manifold to classify text.
A new method for MARL with partial observations reduces communication overhead.
problem Inefficient MARL algorithms in large-scale problems due to state and action information sharing.
method Distributed zeroth-order policy optimization with local policy gradient estimation using consensus.
result The method converges to a policy that is a stationary point of the global objective function.
The paper tackles statistical and computational challenges in learning correlated reward models.
problem The Independence of Irrelevant Alternatives (IIA) assumption collapses human preferences into a universal utility function, leading to coarse approximations.
method The paper investigates the statistical and computational challenges of learning a correlated probit model using best-of-three preference data.
result Best-of-three preference data overcomes the limitations of pairwise preference data, allowing for more fine-grained modeling of human preferences.
RLHF uses human feedback to train AI models, posing statistical challenges.
problem Aligning AI models with human preferences using noisy, subjective feedback.
method Supervised fine-tuning, reward modeling, policy optimization, statistical ideas.
result Statistical methods for reward function learning and policy optimization.
Proposes BSI for valid statistical inference on bandit algorithms.
problem Valid statistical inference on bandit algorithms' performance.
method Fits a simulator of the bandit environment from observed data and uses it to estimate mean reward under any policy.
result Proves asymptotically valid confidence intervals and maintains nominal coverage.
Proposes reducing random error in stochastic optimization by variance regularization.
problem Random error accumulation in stochastic optimization algorithms.
method Regularizes learning-rate based on mini-batch variances.
result Speeds up convergence and stabilizes stochastic optimization.
New IDS algorithm refines parameter norm bounds for better bandit performance.
problem Frequentist IDS requires tight norm bounds, which are often unavailable in practice.
method Iteratively refines a high-probability upper bound on true parameter norm using data.
result Regret bounds independent of assumed parameter norm, outperforming state-of-the-art algorithms.
Market making is a fundamental trading problem in which an agent provides liquidity by continually offering to buy and sell a security. The problem is challenging due to inventory risk, the risk of accumulating an unfavourable position and ultimately losing money. In this paper, we develop a high-fidelity simulation of…
Statistical fields model explains capital allocation and accumulation among firms and investors.
problem Understanding capital allocation and accumulation dynamics among firms and investors.
method Applied statistical fields formalism to heterogeneous agents divided into firms and investors.
result Capital accumulation depends on various factors including long-term returns, competition, and stock price volatility.
A deep reinforcement learning method for cost-sensitive portfolio selection.
problem Non-stationary price series and complex asset correlations make feature learning hard, and practical cost constraints are not considered.
method A two-stream portfolio policy network and a cost-sensitive reward function are developed using deep reinforcement learning.
result The method achieves superior performance in profitability, cost-sensitivity, and representation abilities.
We extend Bayesian multi-armed bandit (MAB) algorithms beyond their original setting by making use of sequential Monte Carlo (SMC) methods. A MAB is a sequential decision making problem where the goal is to learn a policy that maximizes long term payoff, where only the reward of the executed action is observed. In the …
New algorithm tackles delayed feedback in Lipschitz bandits with sublinear regret.
problem Delayed feedback in Lipschitz bandits.
method Design of algorithms for bounded and unbounded stochastic delays.
result Sublinear regret guarantees for both bounded and unbounded delays.
DDO-RM improves reward-based policies by converting reward scores into a target distribution.
problem Improving reward-based policies when the reward function is simpler than the policy.
method Converts reward scores into a target distribution and uses KL-regularized mirror-descent updates.
result DDO-RM outperforms DPO in pair accuracy and mean margin.