CARMS improves gradient estimation for categorical variables.
problem Accurately backpropagating gradients through categorical variables.
method CARMS combines REINFORCE with antithetic sampling to create unbiased gradient estimators.
result CARMS outperforms competing methods on various tasks.
Distributional approaches to value-based reinforcement learning model the entire distribution of returns, rather than just their expected values, and have recently been shown to yield state-of-the-art empirical performance. This was demonstrated by the recently proposed C51 algorithm, based on categorical distributiona…
Enhanced reinforcement learning using ensemble methods.
problem Improving reinforcement learning performance.
method Distributional reinforcement learning with ensemble group-aided training.
result Ensemble methods lead to more robust and efficient learning.
A new gradient estimator for categorical distributions reduces bias and variance.
problem Intractability of gradients for categorical distributions in discrete latent variable models.
method CatLog-Derivative trick and IndeCateR gradient estimator.
result IndeCateR reduces bias and variance of gradients for categorical distributions.
New RL algorithm minimizes distributional learning error.
problem Improving distributional reinforcement learning for better error minimization.
method Proposes a new model-based algorithm with theoretical minimax optimality.
result Proves minimax optimality for approximating return distributions.
Survey categorizes methods for learning state representations in reinforcement learning.
problem Addressing challenges in complex observation spaces for sequential decision making.
method Categorizes six main classes of methods for learning state representations.
result Enhances understanding of state representation learning in reinforcement learning.
To address the challenge of backpropagating the gradient through categorical variables, we propose the augment-REINFORCE-swap-merge (ARSM) gradient estimator that is unbiased and has low variance. ARSM first uses variable augmentation, REINFORCE, and Rao-Blackwellization to re-express the gradient as an expectation und…
Researchers propose better probabilistic models for deep learning.
problem Using cross-entropy loss for non-categorical data.
method Introducing continuous-categorical distribution and proposing probabilistic alternatives.
result Potential for outperformance in deep learning models with proper probabilistic treatment.
A new catnat function improves gradient descent for categorical variables.
problem Gradient descent challenges with discrete latent categorical variables.
method Replaced softmax with catnat, a hierarchical binary split function.
result Catnat function offers significant advantages in gradient descent.
Optimization of hyper-parameters in reinforcement learning (RL) algorithms is a key task, because they determine how the agent will learn its policy by interacting with its environment, and thus what data is gathered. In this work, an approach that uses Bayesian optimization to perform a two-step optimization is propos…
Adaptive correlated MC improves sequence generation stability.
problem High gradient variance in reinforcement learning for sequence generation.
method Adapts policy gradient estimator using correlated Monte Carlo rollouts.
result Reduces gradient variance and improves model performance.
The study categorizes reward errors in reinforcement learning, finding some can be beneficial.
problem Training language models with imperfect proxy rewards.
method Theoretical analysis of policy gradient optimization and categorization of reward errors.
result Reward errors can be benign or even beneficial, preventing policy from stalling.
New method learns disentangled discrete representations using categorical variational autoencoders.
problem Learning disentangled representations from discrete latent spaces.
method Replaced standard Gaussian VAE with a categorical VAE to mitigate rotational invariance.
result Categorical distributions improve learning of disentangled representations.
Reward-poisoning attacks can force RL agents to learn bad policies, and we categorize and quantify their feasibility.
problem Reward-poisoning attacks can manipulate RL agents to learn undesirable policies.
method Categorize attacks by infinity-norm constraint, provide thresholds for feasibility, and develop adaptive attack strategies.
result Adaptive reward-poisoning attacks can achieve the nefarious policy in polynomial steps, while non-adaptive attacks require exponential steps.
Survey explores how transfer learning improves deep reinforcement learning.
problem Challenges in reinforcement learning efficiency and effectiveness.
method Categorizes and analyzes transfer learning approaches.
result Transfer learning enhances reinforcement learning performance.
Paper proposes a novel trading strategy combining clustering and reinforcement learning for multi-period portfolio management.
problem Developing an effective trading strategy for multi-period portfolio management.
method The paper integrates clustering techniques with reinforcement learning to categorize and manage stocks across multiple trading periods.
result The proposed strategy outperforms conventional techniques in various metrics, achieving an average return of 151% over 360 trading periods.
New gradient estimators for discrete variables improve model training.
problem Training models with discrete latent variables is challenging due to high gradient variance.
method Introduced novel gradient estimators based on importance sampling and statistical couplings, extending to categorical variables.
result Proposed gradient estimators outperform previous methods in systematic experiments.
Algorithm learns to solve tasks by gradually expanding policy space.
problem Reinforcement learning difficulty progression.
method Decreasingly constrained policy space expansion.
result Superior learning rate in Tetris tasks.
This paper analyzes generalization issues in deep reinforcement learning.
problem Understanding and improving generalization capabilities of deep reinforcement learning policies.
method Formalizing and categorizing solutions to address overfitting in deep reinforcement learning.
result A comprehensive analysis of generalization challenges and solutions in deep reinforcement learning.
This paper studies the potential of the return distribution for exploration in deterministic reinforcement learning (RL) environments. We study network losses and propagation mechanisms for Gaussian, Categorical and Gaussian mixture distributions. Combined with exploration policies that leverage this return distributio…
Study uses RL to optimize dynamic portfolios, addressing non-stationarity and constraints.
problem Non-stationarity and investment constraints in dynamic portfolio optimization.
method Reinforcement learning with regime change variables and practical constraints integration.
result Enhanced prediction accuracy through incorporation of regime change variables.
This paper shows using classification instead of regression improves deep RL scalability.
problem Challenges in training value functions for large networks in deep RL.
method Used categorical cross-entropy loss instead of mean squared error regression.
result Significant improvements in performance and scalability across various domains.
Simpler one-step distributional RL framework for control.
problem Lack of a unified theory for DistrRL in control.
method One-step distributional reinforcement learning (OS-DistrRL) framework.
result Unified theory for policy evaluation and control.
Recently, generating adversarial examples has become an important means of measuring robustness of a deep learning model. Adversarial examples help us identify the susceptibilities of the model and further counter those vulnerabilities by applying adversarial training techniques. In natural language domain, small pertu…
New algorithms for multivariate RL improve decision-making in complex systems.
problem Complex multi-objective decision-making in reinforcement learning.
method Oracle-free and computationally-tractable algorithms for multivariate distributional RL.
result Convergence rates match scalar reward settings and provide insights into reward dimensionality.
Survey of integrating planning and learning in model-based reinforcement learning.
problem Sequential decision making in AI, formalized as MDP optimization.
method Systematic coverage of dynamics model learning and planning-learning integration.
result Broad conceptual overview of model-based reinforcement learning.
This paper extends rack and quandle covering theory using higher categorical Galois theory.
problem Developing a higher covering theory of racks and quandles.
method Applying techniques from higher categorical Galois theory to extend and clarify the foundations of rack and quandle coverings.
result Identification of meaningful higher-dimensional centrality conditions defining higher coverings of racks and quandles.
Survey of deep RL in intelligent transportation systems.
problem Optimizing traffic signals and autonomous driving using deep RL.
method Comprehensive review of deep RL applications in traffic control and autonomous driving.
result Summarizes existing works in deep RL-based transportation applications.
This paper generalizes graph representation for diverse data types.
problem Representing and querying hybrid data types in a unified way.
method Introducing a directed Tensor-Typed Multi-Graph with embeddings.
result Unified representation for visual, linguistic, and auditory data.
SymCircuit learns PC structure via entropy-regularized RL, improving inference efficiency and accuracy.
problem Greedy algorithms in PC structure learning lead to suboptimal solutions.
method Entropy-regularized reinforcement learning to train a learned generative policy for PC structure inference.
result SymCircuit learns the optimal policy as a tempered Bayesian posterior, improving inference efficiency and accuracy.
New algorithms improve distributional TD learning with linear approximations.
problem Estimating return distributions in reinforcement learning.
method Fine-grained analysis of linear-categorical Bellman equation, variance reduction techniques.
result Tight sample complexity bounds for distributional TD learning with linear approximations.
Designs a framework to transfer causal models between similar environments.
problem Transferability of causal models between different but similar environments.
method Object-oriented representations and continuous optimization for structure learning.
result Demonstrates advantages in gridworld settings using reinforcement learning.
StructureBoost improves gradient boosting for complex categorical variables efficiently.
problem Efficiently handling complex categorical variables with known structure.
method Two methods to overcome computational obstacles in SCDT enumeration for structured categorical variables.
result StructureBoost outperforms existing packages on complex categorical problems.
Categorical bundles provide a natural framework for gauge theories involving multiple gauge groups. Unlike the case of traditional bundles there are distinct notions of triviality, and hence also of local triviality, for categorical bundles. We study categorical principal bundles that are product bundles in the categor…
Off-policy evaluation (OPE) in both contextual bandits and reinforcement learning allows one to evaluate novel decision policies without needing to conduct exploration, which is often costly or otherwise infeasible. The problem's importance has attracted many proposed solutions, including importance sampling (IS), self…
Survey of RL methods for optimizing power grid topologies.
problem Optimizing power grid operation with adaptive control strategies.
method Reinforcement Learning (RL) for dynamic and uncertain environments.
result Comprehensive evaluation of RL-based methods for power grid topology optimization.
Bayesian model improves categorization of explosions from sparse data.
problem Challenges in categorizing explosions from limited data.
method Bayesian update to Event Categorization Matrix model with Bayesian Decision Theory.
result Consistent gains in overall accuracy and lower false negative rates.
A deep RL approach generates counterfactual instances efficiently.
problem Efficient generation of counterfactual instances for large datasets and diverse models.
method Deep reinforcement learning to optimize counterfactual instances in a single forward pass.
result Model-agnostic and scalable counterfactual generation.
UNTIE learns representations of coupled categorical data.
problem Challenges in learning from unlabeled categorical data with complex couplings.
method UNTIE approach for unsupervised representation learning of heterogeneous couplings.
result UNTIE significantly improves categorical data representations on 25 diverse datasets.
Paper introduces Categorical Normalizing Flows for better handling of categorical data.
problem Limited application of normalizing flows on categorical data due to lack of intrinsic order.
method Categorical Normalizing Flows use continuous transformations to model latent relations in categorical data, optimizing both continuous representation and model likelihood.
result GraphCNF, a permutation-invariant generative model, outperforms state-of-the-art on molecule generation.
This paper proposes a method to reduce complexity in GLMs with categorical predictors.
problem Wasteful, hard-to-interpret, and prone to overfitting of traditional one-hot encoding for high-cardinality categorical predictors.
method Clustering categories of categorical predictors through a numerical method that preserves or improves accuracy while reducing the number of coefficients.
result Clustering categories of categorical predictors reduces complexity substantially without harming accuracy.
The paper shows how integrating categorical semantics can enhance unsupervised domain translation.
problem Improving unsupervised domain translation between perceptually different domains.
method Learning invariant categorical semantic features in an unsupervised manner and conditioning them on the style encoder.
result Conditioning the style encoder on learned categorical semantics improves translation and stylization.
Categorical variables are a natural choice for representing discrete structure in the world. However, stochastic neural networks rarely use categorical latent variables due to the inability to backpropagate through samples. In this work, we present an efficient gradient estimator that replaces the non-differentiable sa…
Survey of RL algorithms for dynamic environments.
problem Handling changing operating conditions in RL.
method Survey of algorithms developed for non-stationary environments.
result Methods to adapt to varying operating conditions.
Study categorizes mutual funds using natural language processing from unstructured data.
problem Categorizing mutual funds using unstructured data for financial analysis.
method Used natural language processing models to classify mutual funds from their investment strategy descriptions.
result High accuracy in categorizing mutual funds using NLP from unstructured data.
Develops 2-categorical methods for multi-parameter persistence.
problem Fundamental limitations of traditional persistence modules.
method 2-categorical structures to capture hierarchical interactions.
result New invariants effectively characterize multidimensional topological features.
Inverse reinforcement learning (IRL) is the problem of inferring the reward function of an agent, given its policy or observed behavior. Analogous to RL, IRL is perceived both as a problem and as a class of methods. By categorically surveying the current literature in IRL, this article serves as a reference for researc…
Transforms classical connections using pushforwards and gauge transformations.
problem Transforming classical connections in categorical settings.
method Constructing pushforwards and applying gauge transformations to decorated path spaces.
result Combines traditional gauge transformation with affine translation.