Black-box optimizers that explore in parameter space have often been shown to outperform more sophisticated action space exploration methods developed specifically for the reinforcement learning problem. We examine these black-box methods closely to identify situations in which they are worse than action space explorat…
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 “parameter exploration”
New algorithm learns optimal exploration parameters for contextual bandits.
problem Learning optimal exploration in contextual bandits.
method Proposes two algorithms that learn optimal exploration parameters online based on context and reward.
result Demonstrates improved performance in learning optimal exploration compared to traditional methods.
This paper proposes an exploration method for deep reinforcement learning based on parameter space noise. Recent studies have experimentally shown that parameter space noise results in better exploration than the commonly used action space noise. Previous methods devised a way to update the diagonal covariance matrix o…
New findings on when to use action space exploration in reinforcement learning.
problem Understanding when to use action space exploration over traditional methods.
method Theoretical analysis and empirical testing of simple exploration methods.
result Exploration in action space is preferred when parametric complexity exceeds action space dimensionality and horizon length.
Syndicated Bandits: A Framework for Auto Tuning Hyper-parameters in Contextual Bandit Algorithmsstat.ML
A framework for auto-tuning hyper-parameters in contextual bandit algorithms.
problem Auto-tuning hyper-parameters in real-time for contextual bandit algorithms.
method Proposes a Syndicated Bandits framework to learn multiple hyper-parameters dynamically.
result Achieves optimal regret bounds under certain scenarios and handles multiple contextual bandit algorithms.
Optimizes exploration for nonlinear systems to learn controllers efficiently.
problem Learning optimal controllers for unknown nonlinear systems.
method Formally quantifies which parameters are most critical, and develops an algorithm to efficiently explore these parameters.
result Proves a near-instance-optimal rate for learning controllers.
In complex simulation environments, certain parameter space regions may result in non-convergent or unphysical outcomes. All parameters can therefore be labeled with a binary class describing whether or not they lead to valid results. In general, it can be very difficult to determine feasible parameter regions, especia…
We propose a framework based on distributional reinforcement learning and recent attempts to combine Bayesian parameter updates with deep reinforcement learning. We show that our proposed framework conceptually unifies multiple previous methods in exploration. We also derive a practical algorithm that achieves efficien…
CAE repurposes critics for efficient exploration in RL.
problem Challenges in reinforcement learning, especially exploration.
method Repurposing value networks in RL algorithms for exploration.
result Provably sub-linear regret bounds and strong empirical stability.
The estimation of unknown values of parameters (or hidden variables, control variables) that characterise a physical system often relies on the comparison of measured data with synthetic data produced by some numerical simulator of the system as the parameter values are varied. This process often encounters two major d…
A simple uncertainty measure improves deep bandit performance.
problem Efficient exploration in complex environments with deep neural networks.
method Sample Average Uncertainty (SAU) for estimating outcome uncertainty directly.
result SAU matches the uncertainty of Thompson Sampling and its regret bounds.
Deep reinforcement learning (RL) methods generally engage in exploratory behavior through noise injection in the action space. An alternative is to add noise directly to the agent's parameters, which can lead to more consistent exploration and a richer set of behaviors. Methods such as evolutionary strategies use param…
A new exploration strategy for contextual bandits reduces regret and is computationally efficient.
problem Improving exploration in contextual bandits to reduce regret.
method Feature perturbation, injecting randomness directly into feature inputs.
result Achieves worst-case regret bound, surpassing existing methods.
We introduce two approaches for combining neural evolution strategy (NES) and proximal policy optimization (PPO): parameter transfer and parameter space noise. Parameter transfer is a PPO agent with parameters transferred from a NES agent. Parameter space noise is to directly add noise to the PPO agent`s parameters. We…
Bandit learning algorithms typically involve the balance of exploration and exploitation. However, in many practical applications, worst-case scenarios needing systematic exploration are seldom encountered. In this work, we consider a smoothed setting for structured linear contextual bandits where the adversarial conte…
We present a general method for fitting finite mixture models (FMM). Learning in a mixture model consists of finding the most likely cluster assignment for each data-point, as well as finding the parameters of the clusters themselves. In many mixture models, this is difficult with current learning methods, where the mo…
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…
An Analysis of the Value of Information when Exploring Stochastic, Discrete Multi-Armed Banditscs.AI
In this paper, we propose an information-theoretic exploration strategy for stochastic, discrete multi-armed bandits that achieves optimal regret. Our strategy is based on the value of information criterion. This criterion measures the trade-off between policy information and obtainable rewards. High amounts of policy …
In this paper we explore the parameter efficiency of BERT arXiv:1810.04805 on version 2.0 of the Stanford Question Answering dataset (SQuAD2.0). We evaluate the parameter efficiency of BERT while freezing a varying number of final transformer layers as well as including the adapter layers proposed in arXiv:1902.00751. …
Proposes EVE for efficient exploration in reinforcement learning.
problem Efficient exploration in reinforcement learning.
method EVE: a recipe for posterior over parameters, facilitating efficient exploration.
result Competitive performance on benchmarks, efficient exploration confirmed.
Large learning rates cause parameter instability, leading to better generalization.
problem Understanding why deep neural networks perform well despite operating outside the traditional stability regime.
method Analyzing the effect of large learning rates on the orientation of Hessian eigenvectors and parameter exploration.
result Large learning rates induce parameter instability, leading to better generalization through exploration of flatter regions of the loss landscape.
Proposes an amortized variational framework for Deep Q Networks.
problem Efficient exploration in deep reinforcement learning.
method Amortized variational inference for action value function approximation.
result Significantly less learning parameters and better performance.
Sampling one or more effective solutions from large search spaces is a recurring idea in machine learning, and sequential optimization has become a popular solution. Typical examples include data summarization, sample mining for predictive modeling and hyper-parameter optimization. Existing solutions attempt to adaptiv…
This paper investigates the effectiveness of adversarial training in enhancing the robustness of Deep Q-Network (DQN) policies to state-space perturbations. We first present a formal analysis of adversarial training in DQN agents and its performance with respect to the proportion of adversarial perturbations to nominal…
Langevin DQNcs.LG
Algorithms that tackle deep exploration -- an important challenge in reinforcement learning -- have relied on epistemic uncertainty representation through ensembles or other hypermodels, exploration bonuses, or visitation count distributions. An open question is whether deep exploration can be achieved by an incrementa…
Autonomous Materials Discovery Driven by Gaussian Process Regression with Inhomogeneous Measurement Noise and Anisotropic Kernelsphysics.comp-ph
GPR enhances materials discovery by automating parameter space exploration.
problem Automating exploration of large, high-dimensional parameter spaces in materials science.
method Gaussian process regression with inhomogeneous measurement noise and anisotropic kernels.
result Importance and benefits of tuning GPR for materials science experiments.
Addressing the issue of SVMs parameters optimization, this study proposes an efficient memetic algorithm based on Particle Swarm Optimization algorithm (PSO) and Pattern Search (PS). In the proposed memetic algorithm, PSO is responsible for exploration of the search space and the detection of the potential regions with…
We present a 1-parameter family of finite action solutions to the Hitchin's equations and explore some of its basic properties. For a fixed value of the parameter, the solution is smooth. We conclude by showing a multi-particle generalization of our basic solutions.
The paper analyzes the intrinsic exploration terms in policy-gradient algorithms.
problem Exploration in policy-gradient algorithms and its impact on policy optimization.
method Numerical optimization criteria and stochastic gradient analysis.
result Exploration techniques improve policy optimization by smoothing the learning objective and modifying gradient estimates.
Improved Bayesian optimisation method using randomised Gaussian process UCB.
problem Improving performance in Bayesian optimisation.
method Developed a modified Gaussian process upper confidence bound (GP-UCB) acquisition function.
result The method achieves better performance than GP-UCB in various problems.
BO algorithms improve binary and preferential optimization by distinguishing between types of uncertainty.
problem Optimizing expensive functions with binary or pairwise comparisons.
method Proposed new acquisition functions distinguishing between epistemic and aleatoric uncertainty.
result New acquisition functions outperform state-of-the-art heuristics in binary and preferential BO.
Sensitivity Analysis for Active Sampling, with Applications to the Simulation of Analog Circuitsstat.ML
Active sampling improves design space exploration for analog circuits.
problem Efficiently exploring the space of design features in analog circuits with many parameters.
method Combining drastic dimension reduction with sensitivity analysis and Bayesian surrogate modeling for active sampling.
result The proposed active sampling flow outperforms traditional Monte-Carlo sampling.
This paper tackles combinatorial optimization under uncertainty with limited feedback.
problem Tackling combinatorial optimization problems with uncertain or unknown parameters.
method Review of techniques for combinatorial pure exploration with limited bandit feedback.
result Introduction of methods for combinatorial optimization under uncertainty with limited observation.
Modern deep neural networks are typically highly overparameterized. Pruning techniques are able to remove a significant fraction of network parameters with little loss in accuracy. Recently, techniques based on dynamic reallocation of non-zero parameters have emerged, allowing direct training of sparse networks without…
New -Coverage objective simplifies exploration in reinforcement learning.
problem Challenges in exploration for high-dimensional domains.
method Introduces -Coverage objective to enable efficient exploration and planning.
result First computationally efficient algorithms for online reinforcement learning with low coverability.
New approach uses autoregressive models to explore and quantify uncertainty in decision-making.
problem Quantifying and exploring uncertainty in online decision-making.
method Reformulates uncertainty as missing future outcomes, training autoregressive models for next-outcome prediction.
result Establishes a reduction from online learning to offline next-outcome prediction, controlling Bayesian regret by sequence prediction loss.
EVILL uses randomised perturbations to improve exploration in bandit problems.
problem Improving exploration in structured stochastic bandit problems.
method Solves for the minimiser of a linearly perturbed regularised negative log-likelihood function.
result EVILL matches the performance of Thompson-sampling-style methods in theory and practice.
We introduce NoisyNet, a deep reinforcement learning agent with parametric noise added to its weights, and show that the induced stochasticity of the agent's policy can be used to aid efficient exploration. The parameters of the noise are learned with gradient descent along with the remaining network weights. NoisyNet …
We propose a framework that directly tackles the probability distribution of the value function parameters in Deep Q Network (DQN), with powerful variational inference subroutines to approximate the posterior of the parameters. We will establish the equivalence between our proposed surrogate objective and variational i…
The popularity of Bayesian optimization methods for efficient exploration of parameter spaces has lead to a series of papers applying Gaussian processes as surrogates in the optimization of functions. However, most proposed approaches only allow the exploration of the parameter space to occur sequentially. Often, it is…
Paper develops a dynamic Bayesian approach for active learning that optimizes exploration-exploitation balance.
problem Balancing exploration and exploitation in active learning for unknown functions.
method Develops BHEEM, a Bayesian hierarchical approach with approximate Bayesian computation for sampling trade-off parameters.
result BHEEM achieves at least 21% and 11% improvement over pure exploration and exploitation strategies respectively.
Proposes meTS for efficient exploration in correlated bandits.
problem Efficiently explore in bandits with correlated actions.
method Mixed-effect model with Thompson Sampling.
result Bound on Bayes regret with two terms.
Multiparameter regularization and aggregation in the context of polynomial functional regressionstat.ML
Study introduces a new method for multiple parameter regularization in polynomial functional regression.
problem Handling varying regularization parameters in polynomial functional regression.
method Developed a theoretically grounded algorithm for multiple parameter regularization and model aggregation.
result Promising results from evaluations on synthetic and real-world data.
The paper explores MAB strategies for very short horizons, introducing new methods and showing improved performance.
problem Short horizon multi-armed bandit problems in games.
method Regression oracles, forced exploration, UCBT strategy.
result Combination of epsilon-greedy or epsilon-decreasing with regression oracles outperforms other strategies.
The paper characterizes biconservative surfaces in hyperbolic 4-space.
problem Characterizing biconservative surfaces in hyperbolic 4-space.
method Establishing intrinsic conditions and analyzing geometric properties.
result Biconservative surfaces in hyperbolic 4-space satisfy a specific intrinsic condition.
Study shows efficient neural network approach for stochastic bandits.
problem Optimizing decisions in uncertain environments with neural network models.
method OFU-ReLU algorithm that balances exploration and exploitation, using a transformed feature space.
result Achieves regret guarantee for stochastic bandits with ReLU neural networks.
Proposes a method to enhance exploration in RL using temporal difference uncertainties.
problem Challenges in estimating uncertainty in non-tabular reinforcement learning settings.
method Estimates uncertainty over value function using temporal difference errors and incorporates it as an intrinsic reward.
result Demonstrates improved exploration in various tasks, including Deep Sea and Atari 2600 environments.
CORe uses randomization to explore bandit problems without external noise.
problem Exploration in stochastic bandit problems.
method Randomizes past observations to exploit variance in rewards.
result Achieves regret bound in stochastic linear bandits.