Temporal difference learning explained through gradient splitting, improving convergence times.
problem Learning value functions in Markov Decision Processes with linear approximations.
method Interpreting TD learning as gradient splitting and applying convergence proofs from gradient descent.
result Improved convergence times for TD learning, especially with a minor variation.
Quantile TD learning outperforms classical TD learning for value estimation.
problem Temporal-difference learning in reinforcement learning.
method Quantile Temporal-Difference Learning (QTD) for policy evaluation.
result QTD offers superior performance to classical TD learning, even in tabular settings.
Temporal-difference and Q-learning learn feature representations that converge to optimal ones.
problem Understanding how feature representations evolve in temporal-difference and Q-learning with neural networks.
method Mean-field theory applied to overparameterized two-layer neural networks.
result The feature representation converges to the optimal one, generalizing previous results.
Quantile Temporal-Difference learning proved convergent with proof.
problem Lack of theoretical understanding of QTD despite empirical success.
method Proof of convergence using stochastic approximation and non-smooth analysis.
result QTD converges to fixed points with probability 1.
Model predicts travel time under rare conditions using a vector-space model.
problem Predicting travel time under rare temporal conditions (e.g., holidays, school vacations) is challenging due to limited historical data and other temporal changes.
method Presented a vector-space model for encoding rare temporal conditions, allowing coherent representation learning across different conditions.
result Increased performance for travel time prediction over different baselines when using the vector-space encoding for representing the temporal setting.
Video sequences contain rich dynamic patterns, such as dynamic texture patterns that exhibit stationarity in the temporal domain, and action patterns that are non-stationary in either spatial or temporal domain. We show that a spatial-temporal generative ConvNet can be used to model and synthesize dynamic patterns. The…
New methods improve temporal difference learning for policy evaluation in Markov decision processes.
problem Improving temporal difference learning for policy evaluation in Markov decision processes.
method Introduced variance-reduced forms of stochastic approximation to achieve non-asymptotic, instance-dependent optimality.
result Temporal difference learning is strictly suboptimal, but variance-reduced forms achieve optimality up to logarithmic factors.
TD learning reduces prediction error in Markov chain problems.
problem Estimating value functions in Markov chains with temporal inconsistency.
method Temporal difference learning minimizes temporal inconsistency between successive estimates.
result TD learning can significantly reduce mean-squared error in value estimates.
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.
TD-Flow improves long-term predictions in agent learning.
problem Cumulative errors in step-by-step inference of future states.
method Leverages flow-matching techniques and a novel Bellman equation to learn accurate geometric horizon models.
result Significantly reduces errors at long horizons compared to prior methods.
Temporal difference learning and Residual Gradient methods are the most widely used temporal difference based learning algorithms; however, it has been shown that none of their objective functions is optimal w.r.t approximating the true value function V. Two novel algorithms are proposed to approximate the true value…
In this work, we present a method for node embedding in temporal graphs. We propose an algorithm that learns the evolution of a temporal graph's nodes and edges over time and incorporates this dynamics in a temporal node embedding framework for different graph prediction tasks. We present a joint loss function that cre…
In a dynamic network, the neighborhood of the vertices evolve across different temporal snapshots of the network. Accurate modeling of this temporal evolution can help solve complex tasks involving real-life social and interaction networks. However, existing models for learning latent representation are inadequate for …
Improved incremental sequence classification with temporal consistency.
problem Updating predictions as new sequence elements are revealed.
method Temporal-difference learning and a temporal-consistency condition for successive predictions.
result Optimizing a novel loss function improves data efficiency and predictive accuracy.
Paper introduces a new reinforcement learning method with improved performance.
problem Designing and analyzing efficient reinforcement learning algorithms.
method Proximal gradient temporal difference learning (GTD) with accelerated algorithm GTD2-MP.
result GTD algorithms have linear complexity and improved convergence rate.
Multi-step temporal difference (TD) learning is an important approach in reinforcement learning, as it unifies one-step TD learning with Monte Carlo methods in a way where intermediate algorithms can outperform either extreme. They address a bias-variance trade off between reliance on current estimates, which could be …
To act and plan in complex environments, we posit that agents should have a mental simulator of the world with three characteristics: (a) it should build an abstract state representing the condition of the world; (b) it should form a belief which represents uncertainty on the world; (c) it should go beyond simple step-…
Accelerates TD learning for long-horizon reinforcement learning problems.
problem Slow convergence of conventional TD learning in long-horizon tasks.
method Introduces PID Accelerated Temporal Difference (PID TD) learning algorithms.
result Accelerates convergence of TD learning compared to conventional methods.
One of the main obstacles to broad application of reinforcement learning methods is the parameter sensitivity of our core learning algorithms. In many large-scale applications, online computation and function approximation represent key strategies in scaling up reinforcement learning algorithms. In this setting, we hav…
A new correction term improves sample efficiency in deep reinforcement learning.
problem Momentum accumulation in TD learning leads to doubly stale gradients.
method Proposed a correction term to address the issue of doubly stale gradients.
result Improves sample efficiency in policy evaluation.
New method uses MMAF-guided learning for spatio-temporal probabilistic forecasts.
problem Probabilistic forecasting of spatio-temporal data with causal structure.
method Generalized Bayesian methodology, MMAF-guided learning, ensemble of stochastic feed-forward neural networks.
result Forecast performance comparable to, and sometimes better than, deep learning architectures.
New method uses neural networks to forecast spatial-temporal data.
problem Probabilistic forecasting of spatio-temporal data with causal structure.
method MMAF-guided learning with ensemble of stochastic feed-forward neural networks.
result Forecasting remains calibrated across multiple time horizons.
Temporal difference learning (TD) is a simple iterative algorithm used to estimate the value function corresponding to a given policy in a Markov decision process. Although TD is one of the most widely used algorithms in reinforcement learning, its theoretical analysis has proved challenging and few guarantees on its s…
Meta-learning adjusts TD learning's eligibility trace parameter for more efficient reinforcement learning.
problem Efficiently tuning the eligibility trace parameter for temporal difference learning.
method Meta-learning method to adjust eligibility trace parameter state-dependently.
result Improves overall quality of update targets, minimizing target error.
MRIF models dynamic user interests at multiple temporal-ranges.
problem Capturing dynamic and multi-resolution user interests in recommendation.
method Multi-resolution Interest Fusion (MRIF) model that considers both temporal-ranges and drifts in user interests.
result MRIF outperforms state-of-the-art recommendation methods consistently.
A method for fast, accurate cross-temporal forecasts using machine learning.
problem Inconsistent forecasts across different levels of platform data.
method Non-linear hierarchical forecast reconciliation using machine learning.
result Automated direct production of reconciled forecasts for high-frequency decision making.
Improved TD learning with neural nets reduces sample complexity and overparameterization.
problem Temporal difference learning with neural networks in large state spaces.
method Projection-free and max-norm regularized Neural TD learning, with Lyapunov drift analysis.
result Max-norm regularization significantly improves TD learning's sample complexity and overparameterization.
New algorithms improve reinforcement learning stability and performance.
problem Stability issues in TD learning algorithms with function approximation and off-policy sampling.
method Developed and adapted emphatic temporal difference (ETD(λ)) algorithms for deep reinforcement learning. result Demonstrated improved performance in Atari games and small problems.
Paper improves TD learning algorithm bounds with linear approx.
problem Sharp bounds for TD method performance in MDPs.
method Polyak-Ruppert averaging, universal step size, refined error bounds, stability of random matrices.
result Near-optimal variance and bias terms achieved.
Temporal mixture ensemble predicts cryptocurrency exchange volumes better than traditional methods.
problem Intraday volume forecasting in cryptocurrency markets.
method Temporal mixture ensemble model using transaction and order book data.
result The model outperforms traditional time series and machine learning methods.
Novel bounds improve TD learning consistency in RL.
problem Analyzing Temporal Difference learning's performance.
method High-dimensional concentration inequalities and Berry-Esseen bounds for Markov chain induced martingales.
result Sharp high-probability consistency guarantee for TD learning, matching asymptotic variance up to logarithmic factors.
Machine learning struggles with temporal data in finance, leading to inaccurate models.
problem Machine learning models struggle with temporal data in finance, leading to inaccurate predictions.
method Review and critique current machine learning approaches for temporal data in finance.
result Current approaches to machine learning in finance often ignore the temporal richness of data.
GTEA learns node representations in temporal interaction graphs.
problem Inductive representation learning on temporal interaction graphs.
method Integrates sequence model with time encoder and self-attention scheme for edge and node embeddings.
result GTEA learns comprehensive node representations capturing temporal and structural characteristics.
Develops a hybrid deep learning model for stock price prediction.
problem Predicting daily stock prices in the stock market.
method Representation learning with Stock2Vec embedding and temporal convolutional layers.
result Achieves better performance on stock price prediction than benchmarks.
Combines CNN and LSTM for spatio-temporal graph networks.
problem Improving spatio-temporal feature extraction.
method Proposes a new architecture combining CNN and LSTM temporal blocks.
result Empirical comparison shows our model outperforms existing models.
This paper challenges the conventional wisdom about temporal difference learning's superiority in stitching experience.
problem The effectiveness of temporal difference learning in stitching experience across different reinforcement learning methods.
method Empirical study comparing Monte Carlo and temporal difference learning methods in stitching experience.
result Monte Carlo methods can also achieve experience stitching, challenging the conventional wisdom.
Understanding temporal dynamics has proved to be highly valuable for accurate recommendation. Sequential recommenders have been successful in modeling the dynamics of users and items over time. However, while different model architectures excel at capturing various temporal ranges or dynamics, distinct application cont…
TD learning reduces interference, leading to better generalization.
problem Understanding and reducing interference in TD learning for better generalization.
method Analyzing the inner product of gradients as interference, comparing TD and supervised learning, and examining the dynamics of interference and bootstrapping.
result TD learning leads to low-interference, under-generalizing parameters, while supervised learning does the opposite.
Unified framework for PE and TD methods in continuous time and space.
problem Policy evaluation and TD learning in continuous settings.
method Martingale characterization for designing PE algorithms.
result Convergent time-discretized algorithms converge to continuous-time counterparts.
New algorithms for collaborative reinforcement learning with limited communication.
problem Efficiently learning value functions in multi-agent systems with strict information constraints.
method Distributed gradient-based temporal difference algorithms with consensus schemes.
result Parameter estimates converge to ODEs with defined invariant sets under general assumptions.
Off-policy reinforcement learning has many applications including: learning from demonstration, learning multiple goal seeking policies in parallel, and representing predictive knowledge. Recently there has been an proliferation of new policy-evaluation algorithms that fill a longstanding algorithmic void in reinforcem…
Study on reinforcement learning dynamics using statistical physics.
problem Understanding how reinforcement learning dynamics interact with parameters and state features.
method Statistical physics concepts applied to temporal difference learning with linear function approximators.
result Stochastic semi-gradient noise leads to significant plateaus in value error.
Recently, a new multi-step temporal learning algorithm, called Q(σ), unifies n-step Tree-Backup (when σ=0) and n-step Sarsa (when σ=1) by introducing a sampling parameter σ. However, similar to other multi-step temporal-difference learning algorithms, Q(σ) needs much memory consumption and computation tim…
New TD method stabilizes average-reward learning.
problem Stability issues in average-reward TD learning.
method Implicit fixed point update for average-reward TD(λ). result Improved numerical stability and broader step-size range.
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.
Enhances reinforcement learning uncertainty estimation with a generalized Gaussian error model.
problem Inaccurate error representations and compromised uncertainty estimation in conventional uncertainty-aware TD learning.
method Introduces a novel framework for generalized Gaussian error modeling in deep reinforcement learning, incorporating higher-order moments, particularly kurtosis, to improve uncertainty estimation and mitigation.
result Significant performance gains in policy gradient algorithms with the proposed framework.
ReaPER improves learning efficiency by prioritizing reliable experiences.
problem Inefficient sampling of past experiences in reinforcement learning.
method Introducing a novel measure of reliability to prioritize experiences in PER.
result ReaPER outperforms PER in various environments, including Atari-10.
In kernel methods, temporal information on the data is commonly included by using time-delayed embeddings as inputs. Recently, an alternative formulation was proposed by defining a gamma-filter explicitly in a reproducing kernel Hilbert space, giving rise to a complex model where multiple kernels operate on different t…