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.
Evolutionary Strategies optimize hyper-parameters for off-policy learning.
PBVFs generalize across policies using learned value functions.
New NPG variants ensure parameter convergence in multi-agent learning.
This work formalizes and extends parameter sharing in multi-agent reinforcement learning.
Efficient policy learning from observational data using weighted classification reductions.
Restless bandit problems are instances of non-stationary multi-armed bandits. These problems have been studied well from the optimization perspective, where the goal is to efficiently find a near-optimal policy when system parameters are known. However, very few papers adopt a learning perspective, where the parameters…
Policy Gradient (PG) algorithms are among the best candidates for the much-anticipated applications of reinforcement learning to real-world control tasks, such as robotics. However, the trial-and-error nature of these methods poses safety issues whenever the learning process itself must be performed on a physical syste…
Optimizes Thompson sampling policies using policy gradient methods.
We introduce a method for constructing skills capable of solving tasks drawn from a distribution of parameterized reinforcement learning problems. The method draws example tasks from a distribution of interest and uses the corresponding learned policies to estimate the topology of the lower-dimensional piecewise-smooth…
Learning Rate (LR) is an important hyper-parameter to tune for effective training of deep neural networks (DNNs). Even for the baseline of a constant learning rate, it is non-trivial to choose a good constant value for training a DNN. Dynamic learning rates involve multi-step tuning of LR values at various stages of th…
Social Security and other public policies can be viewed as a series of cash in and outflows that depend on parameters such as the age distribution of the population and the retirement age. Given forecasts of these parameters, policies can be designed to be financially stable, i.e., to terminate with a zero balance. If …
On-policy reinforcement learning (RL) algorithms have high sample complexity while off-policy algorithms are difficult to tune. Merging the two holds the promise to develop efficient algorithms that generalize across diverse environments. It is however challenging in practice to find suitable hyper-parameters that gove…
Direct contextual policy search methods learn to improve policy parameters and simultaneously generalize these parameters to different context or task variables. However, learning from high-dimensional context variables, such as camera images, is still a prominent problem in many real-world tasks. A naive application o…
Robust policies improve ICU transfer outcomes by predicting patient deterioration.
New method prevents RLHF alignment collapse by accounting for policy's influence on reward model updates.
Proposes PIC and POIC for measuring task difficulty in RL.
Estimates and infers multi-stage stationary treatment policies with variable selection.
A new method improves policy evaluation in RL by tracking value uncertainties.
The policy gradient approach is a flexible and powerful reinforcement learning method particularly for problems with continuous actions such as robot control. A common challenge in this scenario is how to reduce the variance of policy gradient estimates for reliable policy updates. In this paper, we combine the followi…
Bayesian approach uses Gaussian process for reinforcement learning.
Bayesian optimization adapts domain parameters for more robust robot policies.
We study the problem of identifying the policy space of a learning agent, having access to a set of demonstrations generated by its optimal policy. We introduce an approach based on statistical testing to identify the set of policy parameters the agent can control, within a larger parametric policy space. After present…
A new framework for adaptive behavior using reusable value profiles.
In this paper we target the problem of transferring policies across multiple environments with different dynamics parameters and motor noise variations, by introducing a framework that decouples the processes of policy learning and system identification. Efficiently transferring learned policies to an unknown environme…
New method reduces over-pessimism in Bayesian control under parameter uncertainty.
Optimizes learning policies in average-reward MDPs with improved sample complexity.
Paper analyzes convergence of dynamic policy gradient for MDPs, improving performance in finite-time problems.
Study improves policy search in continuous control by using heavy-tailed distributions.
We propose and analyze an alternate approach to off-policy multi-step temporal difference learning, in which off-policy returns are corrected with the current Q-function in terms of rewards, rather than with the target policy in terms of transition probabilities. We prove that such approximate corrections are sufficien…
Recently, reinforcement learning (RL) algorithms have demonstrated remarkable success in learning complicated behaviors from minimally processed input. However, most of this success is limited to simulation. While there are promising successes in applying RL algorithms directly on real systems, their performance on mor…
The ability to discover approximately optimal policies in domains with sparse rewards is crucial to applying reinforcement learning (RL) in many real-world scenarios. Approaches such as neural density models and continuous exploration (e.g., Go-Explore) have been proposed to maintain the high exploration rate necessary…
The goal of reinforcement learning (RL) is to let an agent learn an optimal control policy in an unknown environment so that future expected rewards are maximized. The model-free RL approach directly learns the policy based on data samples. Although using many samples tends to improve the accuracy of policy learning, c…
Robust Policy Search is the problem of learning policies that do not degrade in performance when subject to unseen environment model parameters. It is particularly relevant for transferring policies learned in a simulation environment to the real world. Several existing approaches involve sampling large batches of traj…
ABPS improves RL training efficiency by sharing policies and evolving hyper-params.
Improving the sample efficiency in reinforcement learning has been a long-standing research problem. In this work, we aim to reduce the sample complexity of existing policy gradient methods. We propose a novel policy gradient algorithm called SRVR-PG, which only requires episodes to find an -approxima…
The paper automates policy learning for nonlinear welfare criteria using machine learning and debiasing techniques.
We present a new method of blackbox optimization via gradient approximation with the use of structured random orthogonal matrices, providing more accurate estimators than baselines and with provable theoretical guarantees. We show that this algorithm can be successfully applied to learn better quality compact policies …
STORM-PG uses momentum for faster policy gradient updates.
The paper interprets policy-gradient algorithms using continuation theory.
Recent developments have established the vulnerability of deep reinforcement learning to policy manipulation attacks via intentionally perturbed inputs, known as adversarial examples. In this work, we propose a technique for mitigation of such attacks based on addition of noise to the parameter space of deep reinforcem…
Greedy policies perform poorly in imperfectly observed contextual bandits.
Paper tackles efficient policy gradient estimation from off-policy data.
Soft modularization improves sample efficiency and performance in reinforcement learning.
This paper proposes a parsimoniously time varying parameter vector autoregressive model (with exogenous variables, VARX) and studies the properties of the Lasso and adaptive Lasso as estimators of this model. The parameters of the model are assumed to follow parsimonious random walks, where parsimony stems from the ass…
Inspired by the seminal work on Stein Variational Inference and Stein Variational Policy Gradient, we derived a method to generate samples from the posterior variational parameter distribution by \textit{explicitly} minimizing the KL divergence to match the target distribution in an amortize fashion. Consequently, we a…
A new policy switching technique improves offline RL performance.
A usual reinsurance policy for insurance companies admits one or two layers of the payment deductions. Under optimal criterion of minimizing the conditional tail expectation (CTE) risk measure of the insurer's total risk, this article generalized an optimal stop-loss reinsurance policy to an optimal multi-layer reinsur…
Effective risk control must make a tradeoff between the microprudential risk of exogenous shocks to individual institutions and the macroprudential risks caused by their systemic interactions. We investigate a simple dynamical model for understanding this tradeoff, consisting of a bank with a leverage target and an unl…