Multi-output Gaussian processes (MOGP) are probability distributions over vector-valued functions, and have been previously used for multi-output regression and for multi-class classification. A less explored facet of the multi-output Gaussian process is that it can be used as a generative model for vector-valued rando…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “value-function discriminator”
Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributionscs.LG
This work provides guarantees for off-policy function estimation under realizability assumptions.
problem Estimating the value function of a policy under user-specified error-measuring distributions.
method The approach involves imposing a flexible regularization on the MIS objectives to account for an arbitrary user-specified distribution.
result Exact characterization of the optimal dual solution that determines the data-coverage assumption in the case of value-function learning.
Q-MMR evaluates policies using reweighted rewards and moment matching.
problem Off-policy evaluation in finite-horizon MDPs.
method Q-MMR learns scalar weights for data points via a moment matching objective against a value-function discriminator class.
result Data-dependent finite-sample guarantee with a dimension-free error bound.
We provide theoretical investigations into off-policy evaluation in reinforcement learning using function approximators for (marginalized) importance weights and value functions. Our contributions include: (1) A new estimator, MWL, that directly estimates importance ratios over the state-action distributions, removing …
We seek to align agent policy with human expert behavior in a reinforcement learning (RL) setting, without any prior knowledge about dynamics, reward function, and unsafe states. There is a human expert knowing the rewards and unsafe states based on his preference and objective, but querying that human expert is expens…
Intertemporal decision making involves choices among options whose effects occur at different moments. These choices are influenced not only by the effect of rewards value perception at different moments, but also by the time perception effect. One of the main difficulties that affect standard experiments involving int…
We approximate derivatives of functions on manifolds by embedding them and applying vector-valued operators.
problem Derivatives of manifold-valued functions are harder to approximate than vector-valued functions.
method Embed the manifold into a higher space, approximate the derivative of the vector-valued function, and project back.
result We provide error bounds for the approximation of manifold-valued function derivatives.
New method calculates Shapley values for uncertain functions.
problem Uncertain value functions in explainable machine learning.
method Definition of Shapley values using probability theory.
result Shapley values can be applied to uncertain functions.
Deep RBVFs improve continuous control in RL.
problem Challenges in finding optimal actions for continuous actions in RL.
method Introduced deep radial-basis value functions (RBVFs) for continuous control.
result RBF-DQN significantly outperforms value-function-only baselines and is competitive with actor-critic algorithms.
This paper studies a recent proposal to use randomized value functions to drive exploration in reinforcement learning. These randomized value functions are generated by injecting random noise into the training data, making the approach compatible with many popular methods for estimating parameterized value functions. B…
The paper improves energy decay estimates for Dir-stationary Q-valued functions and applies them to Liouville-type theorems and continuity.
problem Improving energy decay estimates for Dir-stationary Q-valued functions.
method Establishing improved decay estimates and applying them to derive Liouville-type theorems and continuity.
result Dir-stationary Q-valued functions exhibit the Lebesgue property and reside in a generalized Campanato-Morrey space.
We propose a new perspective on representation learning in reinforcement learning based on geometric properties of the space of value functions. We leverage this perspective to provide formal evidence regarding the usefulness of value functions as auxiliary tasks. Our formulation considers adapting the representation t…
Kernel methods are among the most popular techniques in machine learning. From a frequentist/discriminative perspective they play a central role in regularization theory as they provide a natural choice for the hypotheses space and the regularization functional through the notion of reproducing kernel Hilbert spaces. F…
In this work, we study value function approximation in reinforcement learning (RL) problems with high dimensional state or action spaces via a generalized version of representation policy iteration (RPI). We consider the limitations of proto-value functions (PVFs) at accurately approximating the value function in low d…
We study the use of randomized value functions to guide deep exploration in reinforcement learning. This offers an elegant means for synthesizing statistically and computationally efficient exploration with common practical approaches to value function learning. We present several reinforcement learning algorithms that…
Develops hierarchical reinforcement learning value function approximators.
problem Estimating long-term returns in reinforcement learning with multiple goals.
method Introduces hierarchical universal value function approximators (H-UVFAs) using the options framework.
result Demonstrates generalization and improved performance of H-UVFAs over UVFAs.
Boosts Q-learning by using value function bounds.
problem Efficiently solving new tasks using past experience.
method Derives double-sided bounds on optimal value function and uses them to update Q-function.
result Boosted training performance through alternative Q-function update method.
PBVFs generalize across policies using learned value functions.
problem RL algorithms forget information about old policies when updating value functions to track the learned policy.
method Introduce Parameter-Based Value Functions (PBVFs) that include policy parameters in their inputs, enabling them to generalize across different policies.
result PBVFs enable zero-shot learning of new policies that outperform any policy seen during training.
The paper uses complex-valued functions to simplify plane differential geometry and kinematics.
problem Simplifying complex problems in plane differential geometry and kinematics.
method Consistent use of complex-valued functions of a real variable.
result Derives results in a particularly simple, uniform, and transparent way.
Paper develops efficient RL algorithm for general value function approximation.
problem Lack of theory for RL with general value function approximation.
method Provable efficient RL algorithm using bounded eluder dimension.
result Achieves a regret bound of .
New method for off-policy evaluation in POMDPs using future-dependent value functions.
problem Curse of horizon in off-policy evaluation for POMDPs.
method Develops future-dependent value functions and minimax learning method.
result PAC result and Bellman completeness for the proposed OPE estimator.
New RL method learns value function for many policies using few key states.
problem Evaluate and improve policies in continuous control problems.
method Combines actor-critic architecture and policy embedding to learn a single value function for many policies.
result Value function minimizes prediction error by learning a small set of 'probing states' and their impact on policies' returns.
We propose a plan online and learn offline (POLO) framework for the setting where an agent, with an internal model, needs to continually act and learn in the world. Our work builds on the synergistic relationship between local model-based control, global value function learning, and exploration. We study how local traj…
Novel framework for Bayesian reinforcement learning infers value function distributions.
problem Bayesian reinforcement learning's challenges in inferring value function distributions.
method Inferential Induction framework for Bayesian reinforcement learning, developing Bayesian Backwards Induction algorithm.
result Proposed algorithm is competitive with state-of-the-art methods.
We establish geometric and topological properties of the space of value functions in finite state-action Markov decision processes. Our main contribution is the characterization of the nature of its shape: a general polytope (Aigner et al., 2010). To demonstrate this result, we exhibit several properties of the structu…
Despite recent successes in Reinforcement Learning, value-based methods often suffer from high variance hindering performance. In this paper, we illustrate this in a continuous control setting where state of the art methods perform poorly whenever sensor noise is introduced. To overcome this issue, we introduce Recurre…
Paper tackles robust control of SDEs with ambiguity, proving value function existence and applying to investment problems.
problem Robust control of SDEs with ambiguity parameters and non-Lipschitz coefficients.
method Existence and uniqueness of value function established through BSDEs with non-linear growth conditions.
result Existence and uniqueness of value function in proper space, verified through BSDEs.
We present a fully nonparametric method to estimate the value function, via simulation, in the context of expected infinite-horizon discounted rewards for Markov chains. Estimating such value functions plays an important role in approximate dynamic programming and applied probability in general. We incorporate "soft in…
We show that there is no analog of Kirszbraun's extension theorem for Almgren's multiple valued functions.
PPG separates policy and value function training phases for better reinforcement learning efficiency.
problem Challenges in traditional reinforcement learning methods for policy and value function optimization.
method Integrates Phasic Policy Gradient framework that splits policy and value function training into distinct phases.
result Significantly improves sample efficiency on Procgen Benchmark compared to PPO.
It is well known that quantifying uncertainty in the action-value estimates is crucial for efficient exploration in reinforcement learning. Ensemble sampling offers a relatively computationally tractable way of doing this using randomized value functions. However, it still requires a huge amount of computational resour…
The Bellman error is a poor proxy for value function accuracy, even with all state-action pairs.
problem The Bellman error is a poor proxy for the accuracy of the value function.
method Study of the Bellman equation as a surrogate objective for value prediction accuracy.
result The magnitude of the Bellman error is only weakly related to the distance to the true value function, even with all state-action pairs.
Randomized value functions offer a promising approach towards the challenge of efficient exploration in complex environments with high dimensional state and action spaces. Unlike traditional point estimate methods, randomized value functions maintain a posterior distribution over action-space values. This prevents the …
Estimating the value function for a fixed policy is a fundamental problem in reinforcement learning. Policy evaluation algorithms---to estimate value functions---continue to be developed, to improve convergence rates, improve stability and handle variability, particularly for off-policy learning. To understand the prop…
The paper describes orbits of circle-valued functions on a 2-torus.
problem Understanding the fundamental groups of orbits of circle-valued functions.
method Algebraic description of fundamental groups of orbits of circle-valued smooth functions.
result An algebraic description of fundamental groups of orbits of circle-valued smooth functions.
The study quantifies and compares aleatoric and epistemic discrimination in ML models.
problem Sources of discrimination in ML models and their impact on performance.
method Quantifying aleatoric and epistemic discrimination using statistical experiments and model accuracy.
result State-of-the-art fairness interventions are effective at removing epistemic discrimination but not aleatoric discrimination in datasets with missing values.
In a discounted reward Markov Decision Process (MDP), the objective is to find the optimal value function, i.e., the value function corresponding to an optimal policy. This problem reduces to solving a functional equation known as the Bellman equation and a fixed point iteration scheme known as the value iteration is u…
A novel approach uses an ensemble of Gaussian processes for robust and adaptive reinforcement learning.
problem Adaptive reinforcement learning in large or continuous state spaces.
method Online scalable (OS) approach with a weighted ensemble of Gaussian processes.
result The ensemble approach improves performance in adversarial settings.
Sparse Attention Guided Dynamic Value Estimation for Single-Task Multi-Scene Reinforcement Learningcs.LG
A new method for estimating joint value functions in multi-scene reinforcement learning.
problem High variance in samples for policy gradient computations in multi-scene environments.
method Sparse attention mechanism over multiple value function hypotheses to approximate the true joint value function.
result Significant improvements in reward scores and enhanced navigation efficiency across OpenAI ProcGen environments.
We give a new proof of the fact that the value function of the finite time horizon American put option for a jump diffusion, when the jumps are from a compound Poisson process, is the classical solution of a free boundary equation. We also show that the value function is across the optimal stopping boundary. Our …
Extends Campanato theory to multi-valued functions for geometric variational problems.
problem Regularity of multi-valued functions in geometric variational problems.
method Adapting Campanato's ideas to multi-valued functions, proving regularity theorems.
result Established regularity for multi-valued harmonic functions and stationary integral varifolds.
Discrimination-aware classification is receiving an increasing attention in data science fields. The pre-process methods for constructing a discrimination-free classifier first remove discrimination from the training data, and then learn the classifier from the cleaned data. However, they lack a theoretical guarantee f…
Discriminator guidance improves autoregressive diffusion models for generating molecular graphs.
problem Improving the accuracy of autoregressive diffusion models for generating molecular graphs.
method Deriving ways to use a discriminator with a pretrained generative model in the discrete case, including optimal and sub-optimal scenarios.
result Using a discriminator can correct pretrained models and improve exact sampling from the data distribution.
Solves GAN mode collapse by assigning minibatches to multiple discriminators.
problem Mode collapse in GANs where models generate similar samples.
method Multiple discriminators, microbatching, and changing tasks.
result Promotes sample diversity in generated sets.
Kernel discriminant analysis uses nonlinear embeddings to improve classification.
problem Limited effectiveness of linear discriminant analysis in capturing nonlinear features.
method Study of nonlinear embeddings in kernel discriminant analysis using polynomial and Gaussian kernels, solving generalized eigenvalue problems.
result Polynomial and Gaussian discriminants capture class differences through population moments and randomized projections.
Establish C^{1,2} regularity of American value functions in Heston model
problem Regularity of American put options in Heston model
method PDE techniques
result C^{1,2} regularity in exercise domain and smooth-fit principle
We introduce Bayesian least-squares policy iteration (BLSPI), an off-policy, model-free, policy iteration algorithm that uses the Bayesian least-squares temporal-difference (BLSTD) learning algorithm to evaluate policies. An online variant of BLSPI has been also proposed, called randomised BLSPI (RBLSPI), that improves…
In this paper we assume the insurance wealth process is driven by the compound Poisson process. The discounting factor is modelled as a geometric Brownian motion at first and then as an exponential function of an integrated Ornstein-Uhlenbeck process. The objective is to maximize the cumulated value of expected discoun…