We propose to use boosted regression trees as a way to compute human-interpretable solutions to reinforcement learning problems. Boosting combines several regression trees to improve their accuracy without significantly reducing their inherent interpretability. Prior work has focused independently on reinforcement lear…
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.
168,657 papers · 148 categories
Trend · papers per month
48 results for “reinforced regression”
In this note we propose a new approach towards solving numerically optimal stopping problems via reinforced regression based Monte Carlo algorithms. The main idea of the method is to reinforce standard linear regression algorithms in each backward induction step by adding new basis functions based on previously estimat…
Reinforced optimal controlmath.OC
Improved reinforcement method for optimal control problems.
problem Optimal control problems with limited computational cost.
method Reinforced least squares Monte Carlo method for stochastic control problems.
result Significant improvement in method's efficiency and accuracy.
WiGS improves active learning for regression by dynamically selecting informative samples.
problem Reducing labeling costs in regression tasks.
method Formulated as a reinforcement learning problem, WiGS adapts the exploration-investigation balance.
result WiGS outperforms static methods in accuracy and labeling efficiency, especially in irregular data density.
A Cramér Distance perspective on Quantile Regression based Distributional Reinforcement Learningstat.ML
This work connects Cramér distance to QR-DQN for DRL.
problem Improving performance in DRL by capturing full distribution of returns.
method Proves Cramér distance's equivalence to 1-Wasserstein distance and proposes a low-complexity algorithm to compute Cramér distance.
result Cramér distance and quantile regression losses yield collinear gradients under non-crossing constraints.
Critic-regularized regression improves offline RL performance.
problem Poor performance of off-policy algorithms in offline RL.
method Critic-regularized regression (CRR) for policy learning from fixed datasets.
result CRR outperforms state-of-the-art offline RL algorithms significantly.
Paper introduces DQPOPE for estimating return distributions in reinforcement learning.
problem Estimating the entire return distribution from off-policy data.
method Deep quantile process regression for distributional off-policy evaluation.
result DQPOPE achieves statistical advantages by estimating full return distribution with same sample size.
Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learningstat.ML
New algorithm mitigates misspecification amplification in regression models with covariate shift.
problem Distribution shift and model misspecification in regression models.
method Developed a new algorithm inspired by robust optimization to avoid misspecification amplification.
result No misspecification amplification while still achieving optimal statistical rates.
Kernel-based function approximation improves reinforcement learning performance.
problem Average reward reinforcement learning in infinite horizon settings.
method Optimistic algorithm based on kernel ridge regression.
result No-regret performance guarantees and confidence intervals for kernel-based predictions.
FFN addresses spectral bias in neural value approximation, improving reinforcement learning performance.
problem Spectral bias in neural value approximation, leading to slow convergence and poor performance.
method Proposes Fourier feature networks (FFN) to overcome spectral bias by using a composite neural tangent kernel.
result FFN achieves state-of-the-art performance on challenging continuous control domains with faster convergence and better stability.
A new trading model uses deep reinforcement learning to optimize portfolio weights.
problem Optimizing portfolio weights with risk and return considerations.
method Improved deep reinforcement learning with actor-critic architecture, quantile regression, and asset short selling.
result The proposed model outperforms benchmark strategies in backtesting.
New approach uses PDE learning for faster RL fine-tuning.
problem Learning optimal control policy for diffusion process.
method Solves variational inequality based on HJB equations.
result Shows fine-tuning can be done via supervised regression.
Control of non-episodic, finite-horizon dynamical systems with uncertain dynamics poses a tough and elementary case of the exploration-exploitation trade-off. Bayesian reinforcement learning, reasoning about the effect of actions and future observations, offers a principled solution, but is intractable. We review, then…
DFIV uses deep neural nets to learn nonlinear features in IV regression.
problem Learning causal relationships from observational data with nonlinear interactions.
method DFIV trains deep neural nets to define nonlinear features on instruments and treatments, alternating training to compose stages 1 and 2.
result DFIV outperforms state-of-the-art methods on IV benchmarks and off-policy policy evaluation.
A new method recovers rewards from behavior policies using classification and regression.
problem Recovering meaningful rewards from observed behavior in reinforcement learning.
method GenPQR, a modular procedure that estimates behavior policy, evaluates soft Q-function, and recovers normalized reward using classification and regression.
result GenPQR matches or improves reward recovery compared to DeepPQR, while being simpler and more modular.
We propose a flexible method for estimating value functions in reinforcement learning without parametric assumptions.
problem Lack of interpretability in reinforcement learning models, especially in healthcare applications.
method Nonparametric additive model using local kernel regression and basis expansion.
result Personalized, adaptive recommendations for postoperative recovery.
Continuous-time reinforcement learning: ellipticity enables model-free value function approximationcs.LG
New algorithm learns value and advantage functions for continuous-time Markov processes without structural assumptions.
problem Learning value and advantage functions for continuous-time Markov processes without structural assumptions.
method Proposes Sobolev-prox fitted -learning algorithm based on Hilbert-space positive definiteness and boundedness properties of Bellman operators.
result Identifies ellipticity as a key structural property enabling reinforcement learning for Markov diffusions.
Paper introduces a new method for improving reinforcement learning performance using transfer learning.
problem Improving reinforcement learning performance with limited sample sizes in dynamic decision-making scenarios.
method Developed a novel ``re-weighted targeting procedure'' and ``transfer deep -learning'' approach.
result Demonstrated improved reinforcement learning performance through strategic sample construction.
UCRL-WVTR tackles long-term reinforcement learning with general approximations, achieving horizon-free and instance-dependent regret bounds.
problem Long-term reinforcement learning with general function approximations.
method UCRL-WVTR proposes a novel algorithm, UCRL-WVTR, with weighted value-targeted regression and a high-order moment estimator.
result Achieves horizon-free and instance-dependent regret bounds matching minimax lower bounds up to logarithmic factors.
OccamNet finds interpretable symbolic fits to data efficiently.
problem Complex neural models extrapolate poorly and are hard to interpret.
method Samples functions, biases towards better fits, and uses cross-entropy matching.
result Outperforms state-of-the-art symbolic regression methods on real-world datasets.
Improved variational inference for logistic regression and classification.
problem Intractability of Evidence Lower Bound in variational logistic regression.
method Introducing a new bound for the expectation of softplus function, applied to variational logistic regression and Gaussian process classification.
result The new bound results in a tighter posterior and faster computation compared to Monte-Carlo methods.
GFN-SR uses deep learning to generate diverse mathematical expressions.
problem Symbolic regression to find best mathematical expressions.
method Traversing a DAG to generate expression trees sequentially with GFlowNet.
result GFN-SR outperforms other SR algorithms in noisy data.
A new hedging strategy uses deep reinforcement learning to manage gamma and vega risks.
problem Managing gamma and vega risks in derivatives trading with stochastic underlying.
method Deep distributional reinforcement learning (D4PG) combined with quantile regression.
result Optimal hedging strategy depends on objective function, transaction costs, and option maturity.
RWR converges to global optimum in certain settings.
problem Proving convergence of RWR to optimal policy.
method Iterative learning with return-weighted log-likelihood.
result RWR converges to global optimum under certain conditions.
VOL optimizes RL with sparse rewards using weighted bounds.
problem Sparse rewards and non-linear function approximation in RL.
method VOL combines -learning with weighted bounds for optimal regret.
result Achieves asymptotically optimal regret for linear function approximation.
New principle optimizes bandit decisions with context.
problem Dealing with general function classes and large context spaces in bandits.
method Upper Counterfactual Confidence Bounds (UCCB) principle.
result Proves optimality and efficiency in complex settings.
Proposes a method to estimate policy values in reinforcement learning with unmeasured confounders.
problem Estimating policy values in reinforcement learning with unmeasured confounders.
method Develops a two-way deconfounder algorithm using a neural tensor network to learn unmeasured confounders and system dynamics.
result Consistent policy value estimation through model-based estimator.
This paper proposes GProp, a deep reinforcement learning algorithm for continuous policies with compatible function approximation. The algorithm is based on two innovations. Firstly, we present a temporal-difference based method for learning the gradient of the value-function. Secondly, we present the deviator-actor-cr…
Linear Bellman Completeness Suffices for Efficient Online Reinforcement Learning with Few Actionscs.LG
Polynomial-time RL algorithm for constant actions under linear Bellman completeness.
problem Efficient online reinforcement learning with few actions.
method Polynomial-time algorithm based on linear function approximation.
result First computationally efficient algorithm for RL with constant actions under linear Bellman completeness.
GPs with neural network dual kernels improve reinforcement learning performance.
problem Combining the strengths of DNNs and GPs for reinforcement learning.
method Apply GPs with neural network dual kernels to solve reinforcement learning tasks.
result GPs with neural network dual kernels perform at least as well as conventional methods on the mountain-car problem.
The paper improves reinforcement learning stability and efficiency with a new theoretical framework.
problem Stability and efficiency in reinforcement learning, especially in data-scarce scenarios.
method Theoretical framework using resampled - and -statistics to model experience replay, applied to policy evaluation and kernel ridge regression.
result Significant improvements in stability and efficiency, particularly in data-scarce scenarios.
Introduces NQ network for non-crossing quantile learning.
problem Quantile crossing issue in distributional learning.
method Non-negative activation functions ensure monotonic distributions.
result Effective for distributional reinforcement learning and causal effect estimation.
SMRL uses score matching for efficient RL with exponential family models.
problem Efficient reinforcement learning with unknown transition models.
method Score matching for parameter estimation of exponential family models.
result Achieves online regret of .
The paper proposes a learning algorithm that improves adaptability and generalization.
problem Improving adaptability and generalization in learning models.
method Learning to meta-learn by meta-finetuning on related tasks before adapting to specific tasks.
result Learning to meta-learn improves adaptability and generalization across various tasks.
In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that uses standard supervised learning methods as subroutines. Our goal is an algorithm that utilizes only simple and convergent maximum likelihood loss functions, while also being able to leverage off-policy data. Our proposed appr…
This paper proposes RDS to improve model diversity in data sampling.
problem Data selection process can lead to performance issues in machine learning models.
method Formulates optimisation problem for model diversification, introduces diverse base learners and ensemble reward mechanisms.
result RDS method enhances model performance on various datasets.
RL learns to ignore factors in factor investing portfolios.
problem Combining factor investing and reinforcement learning for optimal portfolio allocation.
method RL agent learns through sequential allocations based on firms' characteristics using Dirichlet distributions.
result RL-based portfolios are very close to equally-weighted allocations, indicating agnostic factor learning.
Study on regression with Markovian data, establishing limits and proposing an improved algorithm.
problem Least squares regression with dependent Markovian data.
method Sharp information theoretic lower bounds, analysis of SGD-DD and SGD, experience replay algorithm.
result Experience replay algorithm outperforms SGD-DD in Markovian data regression.
The neural linear model is a simple adaptive Bayesian linear regression method that has recently been used in a number of problems ranging from Bayesian optimization to reinforcement learning. Despite its apparent successes in these settings, to the best of our knowledge there has been no systematic exploration of its …
New RL algorithm achieves nearly optimal performance for linear MDPs.
problem Optimal reinforcement learning for episodic linear MDPs.
method Weighted linear regression with variance estimator and rare-switching policy.
result Achieves nearly minimax optimal regret .
In reinforcement learning an agent interacts with the environment by taking actions and observing the next state and reward. When sampled probabilistically, these state transitions, rewards, and actions can all induce randomness in the observed long-term return. Traditionally, reinforcement learning algorithms average …
Single model estimates ensemble uncertainty efficiently.
problem Efficient uncertainty quantification in deep learning models.
method Contextual similarity distillation, approximating ensemble variance with a single model.
result Single model estimates predictive variance with a single forward pass.
New approach connects reinforcement learning robustness and regularization.
problem Dealing with external uncertainty in reinforcement learning.
method Introducing Wasserstein distributionally robust MDPs and a new regularizer.
result Established a dual relation between robust MDPs and regularization.
Improves neural network search in combinatorial spaces of mathematical symbols.
problem Early commitment and initialization bias limit exploration in neural network search.
method Entropy regularization and distribution initialization methods.
result Improves performance, increases sample efficiency, lowers solution complexity.
Reinforcement learning algorithms can solve dynamic decision-making and optimal control problems. With continuous-valued state and input variables, reinforcement learning algorithms must rely on function approximators to represent the value function and policy mappings. Commonly used numerical approximators, such as ne…
A novel approach for safe offline RL using latent safety constraints.
problem Balancing safety constraints and reward maximization in offline RL.
method Conditional Variational Autoencoders for latent safety modeling, Constrained Reward-Return Maximization.
result Our approach maintains safety compliance while optimizing rewards, outperforming existing methods.
This paper shows using classification instead of regression improves deep RL scalability.
problem Challenges in training value functions for large networks in deep RL.
method Used categorical cross-entropy loss instead of mean squared error regression.
result Significant improvements in performance and scalability across various domains.
A simple approach to obtaining uncertainty-aware neural networks for regression is to do Bayesian linear regression (BLR) on the representation from the last hidden layer. Recent work [Riquelme et al., 2018, Azizzadenesheli et al., 2018] indicates that the method is promising, though it has been limited to homoscedasti…