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.
Optimizes control of noisy discrete systems without system matrix knowledge.
The OGY method is one of control methods for a chaotic system. In the method, we have to calculate a stabilizing periodic orbit embedded in its chaotic attractor. Thus, we cannot use this method in the case where a precise mathematical model of the chaotic system cannot be identified. In this case, the delayed feedback…
This paper compares model-based and model-free control methods using neural networks.
The paper presents a model-free method for stabilizing unknown control systems.
Unified reinforcement learning methods using hybrid inference.
New algorithm borrows future randomness to stabilize model-free control.
New model-free algorithm achieves similar LQR regret guarantees.
Model-free approaches for reinforcement learning (RL) and continuous control find policies based only on past states and rewards, without fitting a model of the system dynamics. They are appealing as they are general purpose and easy to implement; however, they also come with fewer theoretical guarantees than model-bas…
Recent success in deep reinforcement learning for continuous control has been dominated by model-free approaches which, unlike model-based approaches, do not suffer from representational limitations in making assumptions about the world dynamics and model errors inevitable in complex domains. However, they require a lo…
Safe RL-based vibration control using LQR guidance.
MFRL-BI controls manufacturing processes without needing accurate models.
The effectiveness of model-based versus model-free methods is a long-standing question in reinforcement learning (RL). Motivated by recent empirical success of RL on continuous control tasks, we study the sample complexity of popular model-based and model-free algorithms on the Linear Quadratic Regulator (LQR). We show…
This research evaluates learning models for bionic robots, focusing on transfer function identification.
Simple model-based reinforcement learning outperforms model-free methods in complex tasks.
Financial portfolio management is one of the problems that are most frequently encountered in the investment industry. Nevertheless, it is not widely recognized that both Kelly Criterion and Risk Parity collapse into Mean Variance under some conditions, which implies that a universal solution to the portfolio optimizat…
Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagined data coupled with a notion of model uncertainty to accelerate the learning of c…
Study compares model-free valuation to actual financial outcomes, finds it slightly conservative.
ACS is an interactive framework for model-free selection with guaranteed error control.
Robotic table tennis learns efficient policies to return balls at 100Hz.
Training an agent to solve control tasks directly from high-dimensional images with model-free reinforcement learning (RL) has proven difficult. A promising approach is to learn a latent representation together with the control policy. However, fitting a high-capacity encoder using a scarce reward signal is sample inef…
MOOSE improves offline RL robustness by using dynamics models.
Hybrid controller combines model-based and policy-based reinforcement learning.
Curriculum learning and imitation learning improve control over financial time-series data.
Unified framework for policy improvement in RL with benefits in data efficiency and computation.
Unified Latent Dynamics unifies model-free and model-based reinforcement learning.
This paper improves robot grasping by integrating meta-control and latent-space imagination.
Delta hedging, which plays a crucial rôle in modern financial engineering, is a tracking control design for a "risk-free" management. We utilize the existence of trends in financial time series (Fliess M., Join C.: A mathematical proof of the existence of trends in financial time series, Proc. Int. Conf. Systems Theory…
Paper develops efficient algorithms for zero-sum Markov games with general function classes.
Dealing with high variance is a significant challenge in model-free reinforcement learning (RL). Existing methods are unreliable, exhibiting high variance in performance from run to run using different initializations/seeds. Focusing on problems arising in continuous control, we propose a functional regularization appr…
Reinforcement learning algorithms are gaining popularity in fields in which optimal scheduling is important, and oncology is not an exception. The complex and uncertain dynamics of cancer limit the performance of traditional model-based scheduling strategies like Optimal Control. Motivated by the recent success of mode…
Paper proposes a privacy-preserving knockoff inference method.
The paper tackles optimal stopping problems using reinforcement learning and singular control.
In many optimization problems in wireless communications, the expressions of objective function or constraints are hard or even impossible to derive, which makes the solutions difficult to find. In this paper, we propose a model-free learning framework to solve constrained optimization problems without the supervision …
This paper proposes a model-free and data-adaptive feature screening method for ultra-high dimensional datasets. The proposed method is based on the projection correlation which measures the dependence between two random vectors. This projection correlation based method does not require specifying a regression model an…
New algorithm tackles non-stationary RL with near-optimal regret bounds.
Simple image augmentation boosts deep RL from pixels.
We provide the first solution for model-free reinforcement learning of ω-regular objectives for Markov decision processes (MDPs). We present a constructive reduction from the almost-sure satisfaction of ω-regular objectives to an almost- sure reachability problem and extend this technique to learning how to control an …
New algorithms for model selection in off-policy evaluation of reinforcement learning.
Integrating model-free and model-based approaches in reinforcement learning has the potential to achieve the high performance of model-free algorithms with low sample complexity. However, this is difficult because an imperfect dynamics model can degrade the performance of the learning algorithm, and in sufficiently com…
We present two different approaches to stochastic integration in frictionless model free financial mathematics. The first one is in the spirit of Itô's integral and based on a certain topology which is induced by the outer measure corresponding to the minimal superhedging price. The second one is based on the controlle…
We propose a novel reformulation of the stochastic optimal control problem as an approximate inference problem, demonstrating, that such a interpretation leads to new practical methods for the original problem. In particular we characterise a novel class of iterative solutions to the stochastic optimal control problem …
Develops a new reinforcement learning framework for complex control problems.
New RL algorithms improve control tasks with data reuse.
A common belief in model-free reinforcement learning is that methods based on random search in the parameter space of policies exhibit significantly worse sample complexity than those that explore the space of actions. We dispel such beliefs by introducing a random search method for training static, linear policies for…
Adversarial methods for imitation learning have been shown to perform well on various control tasks. However, they require a large number of environment interactions for convergence. In this paper, we propose an end-to-end differentiable adversarial imitation learning algorithm in a Dyna-like framework for switching be…
Develops a new model-free approach to portfolio theory using rough paths.
A key challenge for gradient based optimization methods in model-free reinforcement learning is to develop an approach that is sample efficient and has low variance. In this work, we apply Kronecker-factored curvature estimation technique (KFAC) to a recently proposed gradient estimator for control variate optimization…
Develops model-free methods for event history analysis and efficient covariate adjustment.