Paper tackles overestimation bias in continuous control, improving performance by 25%.
problem Overestimation bias in off-policy learning.
method Truncated Quantile Critics (TQC) combines distributional representation, truncation, and ensembling of critics.
result TQC outperforms state-of-the-art methods by 25% on the Humanoid environment.
New dropout technique reduces variance and overestimation in deep Q-Learning.
problem Reduction of variance and overestimation in deep Q-Learning.
method Using Dropout techniques to reduce variance and overestimation in deep Q-Learning.
result Demonstrated effectiveness in enhancing stability and reducing both variance and overestimation.
Q-Learning overestimation bias influenced by learning rate, discount factor, and reward signal.
problem Overestimation bias in Q-Learning algorithm.
method Investigated the influence of learning rate, discount factor, and reward signal on Q-Learning's overestimation bias. Tuned parameters and used an exponential moving average of reward signal.
result Q-Learning can achieve more accurate value estimates by tuning parameters and using an exponential moving average of reward signal.
MFVI can overestimate predictive variance compared to the exact posterior
problem MFVI underestimates posterior variance
method Analyzing conjugate Bayesian Linear Regression
result MFVI can overestimate predictive variance compared to the exact posterior
Reduces overestimation bias in multi-agent RL, improving performance.
problem Value function overestimation bias in multi-agent RL.
method Double centralized critics to reduce overestimation bias.
result Significant improvement in performance on mixed tasks.
Method learns neural network to overestimate reference function with guarantees.
problem Learning a neural network to overestimate a reference function on a given domain.
method Two-step process: constructing Majoring Points and optimizing a neural network.
result The learned neural network overestimates the reference function on the domain.
A widely applicable Bayesian information criterion (Watanabe, 2013) is applicable for both regular and singular models in the model selection problem. This criterion tends to overestimate the log marginal likelihood. We identify an overestimating term of a widely applicable Bayesian information criterion. Adjustment of…
The paper examines various RL algorithms to address overestimation and noise issues.
problem Overestimation and noise in deep reinforcement learning algorithms.
method Analysis of DQN, double DQN, DDPG, TD3, and hill climbing algorithms.
result Optimal noise settings for TD3 in specific environments.
Bayesian models overestimate clusters, but practical summaries can correct this.
problem Bayesian mixture models overestimate the number of clusters.
method Simulations and gene expression data analysis using MCMC summarisation.
result Overestimation is limited in finite samples and can be corrected, but misspecification leads to significant overestimation.
In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies. We show that this problem persists in an actor-critic setting and propose novel mechanisms to minimize its effects on both the actor and the cr…
We correct a mistake in the published version of our paper. Our new conclusion is that the "implied leverage effect" for single stocks is underestimated by option markets for short maturities and overestimated for long maturities, while it is always overestimated for OEX options, except for the shortest maturities wher…
The paper examines skill estimation and variance under model misspecification in IRT.
problem Underestimation and overestimation of skills when non-compensatory model is misspecified as compensatory.
method Theoretical approach to analyze underestimation and overestimation of skills and variance.
result Overestimation of skills occurs around the origin and asymptotic variance differs under model misspecification.
Study shows statistical biases can mislead transformer models, impairing their generalization.
problem Statistical biases in transformers affect their ability to generalize.
method Evaluated transformer models on synthetic algorithmic tasks with varying statistical biases.
result Statistical biases lead to overestimation of transformer models' generalization capabilities.
New model improves volatility forecasting by reducing overestimation and underestimation.
problem SVR-GARCH model overestimates or underestimates volatility, hindering peak or trough behaviors.
method Proposes blending ARCH and augmented blending-ARCH models to improve volatility forecasting.
result Empirical results show improved volatility forecasting ability.
A key problem in research on adversarial examples is that vulnerability to adversarial examples is usually measured by running attack algorithms. Because the attack algorithms are not optimal, the attack algorithms are prone to overestimating the size of perturbation needed to fool the target model. In other words, the…
GUM tackles MARL by avoiding overestimation through state-marginal restriction.
problem Overestimation of values in large joint state-action spaces.
method Greedy UnMixing through state-marginal restriction and unmixing.
result Superior performance compared to existing Q-learning and general MARL algorithms.
Q-Distribution Guided Q-Learning corrects overestimation of uncertain OOD actions in offline RL.
problem Overestimation of Q-values for out-of-distribution actions in offline reinforcement learning.
method QDQ applies a pessimistic adjustment to Q-values in uncertain OOD regions based on a consistency model.
result QDQ improves performance on the D4RL benchmark and achieves significant improvements across many tasks.
Catastrophic forgetting is a critical challenge in training deep neural networks. Although continual learning has been investigated as a countermeasure to the problem, it often suffers from the requirements of additional network components and the limited scalability to a large number of tasks. We propose a novel appro…
Compensation methods correct overestimation of adversarial robustness in neural networks.
problem Overestimation of adversarial robustness using first-order attack methods.
method Proposed compensation methods address inaccurate gradient computation and reduce backpropagations.
result Empirical evaluation of adversarial robustness is improved with these methods.
EMIX minimizes surprise in multi-agent reinforcement learning.
problem Surprise and approximation bias in multi-agent reinforcement learning.
method Energy-based MIXer (EMIX) for minimizing surprise across multiple agents.
result EMIX demonstrates consistent stable performance in challenging StarCraft II scenarios.
Investigates offline RL in factorisable action spaces, overcoming overestimation bias.
problem Overestimation bias in value estimates for unseen state-action pairs.
method Value-decomposition approach in DecQN, adapted for factorised discrete action spaces.
result Demonstrates the effectiveness of factorised approach in offline RL.
SPQR improves Q-ensemble diversity in reinforcement learning.
problem Overestimation bias in Q-learning for complex tasks.
method Introduces SPQR for Q-ensemble independence regularization.
result SPQR outperforms baseline algorithms in online and offline RL benchmarks.
The study aims to prevent unfair content presentation in recommender systems.
problem Over- and under-presentation of content leads to biased user preference estimates.
method Two models are considered: one that ignores systematic and limited exposure, and another that conditions on limited exposure.
result Ignoring systematic presentations overestimates promoted options and underestimates censored alternatives.
Automates bias control in reinforcement learning algorithms.
problem Overestimation bias in reinforcement learning algorithms.
method Data-driven approach for automatic selection of bias control hyperparameters.
result Significant reduction in the number of interactions while maintaining performance.
Markov random fields (MRFs) are difficult to evaluate as generative models because computing the test log-probabilities requires the intractable partition function. Annealed importance sampling (AIS) is widely used to estimate MRF partition functions, and often yields quite accurate results. However, AIS is prone to ov…
In classical Q-learning, the objective is to maximize the sum of discounted rewards through iteratively using the Bellman equation as an update, in an attempt to estimate the action value function of the optimal policy. Conventionally, the loss function is defined as the temporal difference between the action value and…
Paper analyzes finite-time convergence of double Q-learning.
problem Overestimation issue in Q-learning.
method Finite-time analysis of double Q-learning.
result Convergence to ε-accurate neighborhood in finite iterations.
Proposes a conservative LR estimator for infrequent data near a frequency threshold.
problem Overestimation of likelihood ratios for infrequent data near a frequency threshold.
method Conservative likelihood ratio estimator for frequencies slightly above a threshold.
result Improves prediction accuracy in named entity context prediction.
A neural network method improves CVA computations for complex financial portfolios.
problem Improving accuracy of CVA computations for large, diverse portfolios of financial derivatives.
method Proposes a neural network-based approach to adjust exercise strategies for counterparty default risk.
result Shows significant overestimation of CVA by standard methods, especially for non-extreme cases.
New technique prevents Q-learning collapse by maximizing diversity among ensembles.
problem Value function collapse in ensemble Q-learning.
method Maximizing representation diversity through regularization.
result Regularized approach significantly outperforms existing methods.
A novel Q-learning variant reduces underestimation bias in deep actor-critic methods for reinforcement learning.
problem Underestimation bias in deep actor-critic methods for reinforcement learning.
method Introduces a parameter-free Q-learning variant that combines maximum and minimum operators to bound value estimates.
result Improves state-of-the-art performance on OpenAI Gym tasks.
In this paper, we use a new approach to prove that the largest eigenvalue of the sample covariance matrix of a normally distributed vector is bigger than the true largest eigenvalue with probability 1 when the dimension is infinite. We prove a similar result for the smallest eigenvalue.
In the presence of a layer of metaprobabilities (from uncertainty concerning the parameters), the asymptotic tail exponent corresponds to the lowest possible tail exponent regardless of its probability. The problem explains "Black Swan" effects, i.e., why measurements tend to chronically underestimate tail contribution…
Bayesian methods often misinterpret data and asymptotic concepts.
problem Misunderstandings in Bayesian predictive inference.
method Discussion of two specific misunderstandings.
result Consequences of misinterpretations illustrated through examples.
Modern neural networks are highly non-robust against adversarial manipulation. A significant amount of work has been invested in techniques to compute lower bounds on robustness through formal guarantees and to build provably robust models. However, it is still difficult to get guarantees for larger networks or robustn…
We study the phenomenon of bias amplification in classifiers, wherein a machine learning model learns to predict classes with a greater disparity than the underlying ground truth. We demonstrate that bias amplification can arise via an inductive bias in gradient descent methods that results in the overestimation of the…
Paper addresses underestimation bias in double Q-learning, proposing a method to improve learning performance.
problem Underestimation bias in double Q-learning leading to non-optimal fixed points.
method Proposes a simple approach using approximate dynamic programming to bound the target value.
result Significant improvement in learning performance over baseline algorithms in Atari benchmark tasks.
Cold posteriors improve Bayesian neural networks by reducing overestimation of aleatoric uncertainty.
problem Overestimation of aleatoric uncertainty in Bayesian neural networks.
method Tuning the temperature of the posterior on a validation set.
result Reducing temperature leads to better reflection of true prior beliefs.
A new Q-learning variant reduces underestimation bias in deep reinforcement learning.
problem Underestimation bias in deep reinforcement learning policies.
method Introducing a novel, parameter-free Deep Q-learning variant.
result Significantly outperforms existing approaches and improves state-of-the-art performance.
Selective state-adaptive regularization improves offline RL performance.
problem Extrapolation errors and value overestimation in static dataset RL.
method State-adaptive regularization coefficients trust Bellman-driven results selectively.
result Significant improvement in performance on D4RL benchmark.
Investors mispricing volatility and jump sensitivity in Delta hedging models still super-replicate the true claim.
problem Investors misestimate volatility and jump sensitivity in Delta hedging models.
method Analyzes the robustness of Delta hedging in jump-diffusion models, proving stochastic flow properties and convexity of value functions.
result An erroneously computed Delta strategy super-replicates the true claim in expectation under a wide class of models.
What do binary (or probabilistic) forecasting abilities have to do with overall performance? We map the difference between (univariate) binary predictions, bets and "beliefs" (expressed as a specific "event" will happen/will not happen) and real-world continuous payoffs (numerical benefits or harm from an event) and sh…
We propose a robust risk measurement approach that minimizes the expectation of overestimation plus underestimation costs. We consider uncertainty by taking the supremum over a collection of probability measures, relating our approach to dual sets in the representation of coherent risk measures. We provide results that…
This article presents results from the first statistically significant study of traffic forecasts in transportation infrastructure projects. The sample used is the largest of its kind, covering 210 projects in 14 nations worth US$59 billion. The study shows with very high statistical significance that forecasters gener…
We focus on variational inference in dynamical systems where the discrete time transition function (or evolution rule) is modelled by a Gaussian process. The dominant approach so far has been to use a factorised posterior distribution, decoupling the transition function from the system states. This is not exact in gene…
Improved RL policies from offline data with relaxed BC constraints.
problem Overestimation bias in offline RL due to lack of interaction with environment.
method Introducing a policy constraint via behavioural cloning (BC) and adjusting the balance between RL and BC.
result Refined policies outperform baseline and match/exceed complex alternatives.
Small initialization improves tensor recovery from noisy data.
problem Recovering low-tubal-rank tensors from noisy measurements.
method Factorized gradient descent with small initialization.
result Achieves nearly minimax optimal recovery error.
Paper designs a penalty for model order selection using information criteria.
problem Selecting the correct model order from a set of candidate models.
method Designs a penalty for the generalized information criterion (GIC) to minimize underestimation.
result Optimal penalty minimizes underestimation while keeping overestimation below a specified level.