Imagen de Portada

Averaging $n$-step Returns Reduces Variance in Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Daley, Brett, White, Martha, Machado, Marlos C.
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning
por: Daley, Brett, et al.
Publicado: (2023)

Demystifying the Recency Heuristic in Temporal-Difference Learning
por: Daley, Brett, et al.
Publicado: (2024)

An Analysis of Action-Value Temporal-Difference Methods That Learn State Values
por: Daley, Brett, et al.
Publicado: (2025)

Deep Reinforcement Learning with Gradient Eligibility Traces
por: Elelimy, Esraa, et al.
Publicado: (2025)

Harnessing Discrete Representations For Continual Reinforcement Learning
por: Meyer, Edan, et al.
Publicado: (2023)

Deep Double Q-learning
por: Nagarajan, Prabhat, et al.
Publicado: (2025)

AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning
por: Pramanik, Subhojeet, et al.
Publicado: (2023)

DROGO: Default Representation Objective via Graph Optimization in Reinforcement Learning
por: Tse, Hon Tik, et al.
Publicado: (2026)

Reward-Aware Proto-Representations in Reinforcement Learning
por: Tse, Hon Tik, et al.
Publicado: (2025)

Long N-step Surrogate Stage Reward to Reduce Variances of Deep Reinforcement Learning in Complex Problems
por: Zhong, Junmin, et al.
Publicado: (2022)

Plastic Learning with Deep Fourier Features
por: Lewandowski, Alex, et al.
Publicado: (2024)

A Study of Value-Aware Eigenoptions
por: Kotamreddy, Harshil, et al.
Publicado: (2025)

Proper Laplacian Representation Learning
por: Gomez, Diego, et al.
Publicado: (2023)

The Laplacian Keyboard: Beyond the Linear Span
por: Chandrasekar, Siddarth, et al.
Publicado: (2026)

SACn: Soft Actor-Critic with n-step Returns
por: Łyskawa, Jakub, et al.
Publicado: (2025)

The Cell Must Go On: Agar.io for Continual Reinforcement Learning
por: Mohamed, Mohamed A., et al.
Publicado: (2025)

Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning
por: Goodall, Alexander W., et al.
Publicado: (2025)

Empirical Design in Reinforcement Learning
por: Patterson, Andrew, et al.
Publicado: (2023)

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning
por: Schlegel, Matthew, et al.
Publicado: (2026)

Reducing Variance Caused by Communication in Decentralized Multi-agent Deep Reinforcement Learning
por: Zhu, Changxi, et al.
Publicado: (2025)

The Cross-environment Hyperparameter Setting Benchmark for Reinforcement Learning
por: Patterson, Andrew, et al.
Publicado: (2024)

Real-Time Recurrent Learning using Trace Units in Reinforcement Learning
por: Elelimy, Esraa, et al.
Publicado: (2024)

A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning
por: Patterson, Andrew, et al.
Publicado: (2021)

Directions of Curvature as an Explanation for Loss of Plasticity
por: Lewandowski, Alex, et al.
Publicado: (2023)

Reinforcement Learning for Efficient Returns Management
por: Linden, Pascal, et al.
Publicado: (2025)

Laplacian Representations for Decision-Time Planning
por: Shehmar, Dikshant, et al.
Publicado: (2026)

Value Bonuses using Ensemble Errors for Exploration in Reinforcement Learning
por: Wahab, Abdul, et al.
Publicado: (2026)

Position: Benchmarking is Limited in Reinforcement Learning Research
por: Jordan, Scott M., et al.
Publicado: (2024)

Learning Continually by Spectral Regularization
por: Lewandowski, Alex, et al.
Publicado: (2024)

Variance-Reducing Couplings for Random Features
por: Reid, Isaac, et al.
Publicado: (2024)

Rethinking the Foundations for Continual Reinforcement Learning
por: Elelimy, Esraa, et al.
Publicado: (2025)

A New View on Planning in Online Reinforcement Learning
por: Roice, Kevin, et al.
Publicado: (2024)

Reducing Variance in Meta-Learning via Laplace Approximation for Regression Tasks
por: Reichlin, Alfredo, et al.
Publicado: (2024)

TEACH: Temporal Variance-Driven Curriculum for Reinforcement Learning
por: Chaudhary, Gaurav, et al.
Publicado: (2025)

Variance Matters: Improving Domain Adaptation via Stratified Sampling
por: Napoli, Andrea, et al.
Publicado: (2025)

Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence
por: Zhu, Lingwei, et al.
Publicado: (2023)

When is Offline Policy Selection Sample Efficient for Reinforcement Learning?
por: Liu, Vincent, et al.
Publicado: (2023)

Shrinking the Variance: Shrinkage Baselines for Reinforcement Learning with Verifiable Rewards
por: Zeng, Guanning, et al.
Publicado: (2025)

Meta-Learning Reinforcement Learning for Crypto-Return Prediction
por: Wang, Junqiao, et al.
Publicado: (2025)

Mean-Variance Efficient Reinforcement Learning with Applications to Dynamic Financial Investment
por: Kato, Masahiro, et al.
Publicado: (2020)