Imagen de Portada

MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Voelcker, Claas A, Hussing, Marcel, Eaton, Eric, Farahmand, Amir-massoud, Gilitschenski, Igor
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

Dissecting Deep RL with High Update Ratios: Combatting Value Divergence
por: Hussing, Marcel, et al.
Publicado: (2024)

When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning
por: Voelcker, Claas, et al.
Publicado: (2024)

Relative Entropy Pathwise Policy Optimization
por: Voelcker, Claas, et al.
Publicado: (2025)

$λ$-models: Effective Decision-Aware Reinforcement Learning with Latent Models
por: Voelcker, Claas A, et al.
Publicado: (2023)

Calibrated Value-Aware Model Learning with Probabilistic Environment Models
por: Voelcker, Claas, et al.
Publicado: (2025)

Can we hop in general? A discussion of benchmark selection and design using the Hopper environment
por: Voelcker, Claas A, et al.
Publicado: (2024)

Behavior-Consistent Deep Reinforcement Learning
por: Hussing, Marcel, et al.
Publicado: (2026)

Test-Time Graph Search for Goal-Conditioned Reinforcement Learning
por: Opryshko, Evgenii, et al.
Publicado: (2025)

Distributed Continual Learning
por: Le, Long, et al.
Publicado: (2024)

PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling
por: Ma, Avery, et al.
Publicado: (2025)

PID Accelerated Temporal Difference Algorithms
por: Bedaywi, Mark, et al.
Publicado: (2024)

Press Start to Charge: Videogaming the Online Centralized Charging Scheduling Problem
por: Ghahtarani, Alireza, et al.
Publicado: (2026)

Efficient and Accurate Optimal Transport with Mirror Descent and Conjugate Gradients
por: Kemertas, Mete, et al.
Publicado: (2023)

Deflated Dynamics Value Iteration
por: Lee, Jongmin, et al.
Publicado: (2024)

Improving Adversarial Transferability via Model Alignment
por: Ma, Avery, et al.
Publicado: (2023)

A Truncated Newton Method for Optimal Transport
por: Kemertas, Mete, et al.
Publicado: (2025)

Robotic Manipulation Datasets for Offline Compositional Reinforcement Learning
por: Hussing, Marcel, et al.
Publicado: (2023)

Majority of the Bests: Improving Best-of-N via Bootstrapping
por: Rakhsha, Amin, et al.
Publicado: (2025)

Iterative Compositional Data Generation for Robot Control
por: Pham, Anh-Quan, et al.
Publicado: (2025)

Replicable Reinforcement Learning with Linear Function Approximation
por: Eaton, Eric, et al.
Publicado: (2025)

Model Agreement via Anchoring
por: Eaton, Eric, et al.
Publicado: (2026)

Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces
por: Eaton, Eric, et al.
Publicado: (2025)

TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras
por: Mohammadi, Mohammad, et al.
Publicado: (2025)

Update-Free On-Policy Steering via Verifiers
por: Attarian, Maria, et al.
Publicado: (2026)

Augmenting Offline RL with Unlabeled Data
por: Wang, Zhao, et al.
Publicado: (2024)

Temporal-Difference Learning Using Distributed Error Signals
por: Guan, Jonas, et al.
Publicado: (2024)

Sorrel: A simple and flexible framework for multi-agent reinforcement learning
por: Gelpí, Rebekah A., et al.
Publicado: (2025)

SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning
por: Romeo, Carlo, et al.
Publicado: (2025)

Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling
por: Zheng, Shuhong, et al.
Publicado: (2025)

IBCL: Zero-shot Model Generation under Stability-Plasticity Trade-offs
por: Lu, Pengyuan, et al.
Publicado: (2023)

Data Augmentation for Continual RL via Adversarial Gradient Episodic Memory
por: Wu, Sihao, et al.
Publicado: (2024)

Realistic Evaluation of Model Merging for Compositional Generalization
por: Tam, Derek, et al.
Publicado: (2024)

Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates
por: Corrado, Nicholas E., et al.
Publicado: (2023)

Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis
por: Huang, Ruiquan, et al.
Publicado: (2025)

Oracle-Efficient Reinforcement Learning for Max Value Ensembles
por: Hussing, Marcel, et al.
Publicado: (2024)

ReAugment: Model Zoo-Guided RL for Few-Shot Time Series Augmentation and Forecasting
por: Yuan, Haochen, et al.
Publicado: (2024)

Understanding and Exploiting Weight Update Sparsity for Communication-Efficient Distributed RL
por: Miahi, Erfan, et al.
Publicado: (2026)

Sampling Complexity of TD and PPO in RKHS
por: Zou, Lu, et al.
Publicado: (2025)

SPoRt -- Safe Policy Ratio: Certified Training and Deployment of Task Policies in Model-Free RL
por: Cloete, Jacques, et al.
Publicado: (2025)

Data Augmentations for Improved (Large) Language Model Generalization
por: Feder, Amir, et al.
Publicado: (2023)