Imagen de Portada

Uncovering RL Integration in SSL Loss: Objective-Specific Implications for Data-Efficient RL

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Çağatan, Ömer Veysel, Akgün, Barış
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

Failure Modes of Maximum Entropy RLHF
por: Çağatan, Ömer Veysel, et al.
Publicado: (2025)

Higher Resolution, Better Generalization: Unlocking Visual Scaling in Deep Reinforcement Learning
por: Trumpp, Raphael, et al.
Publicado: (2026)

Clipping-Free Policy Optimization for Large Language Models
por: Çağatan, Ömer Veysel, et al.
Publicado: (2026)

SigCLR: Sigmoid Contrastive Learning of Visual Representations
por: Çağatan, Ömer Veysel
Publicado: (2024)

UNSEE: Unsupervised Non-contrastive Sentence Embeddings
por: Çağatan, Ömer Veysel
Publicado: (2024)

NeoRL: Efficient Exploration for Nonepisodic RL
por: Sukhija, Bhavya, et al.
Publicado: (2024)

JigsawRL: Assembling RL Pipelines for Efficient LLM Post-Training
por: Hu, Zhengding, et al.
Publicado: (2026)

Deer-Cora/RL-SSL: RL-SSL
por: Deer-Cora
Publicado: (2026)

Task-Induced Representational Invariances Depend on Learning Objective in Deep RL
por: Halvagal, Manu Srinath, et al.
Publicado: (2026)

Improving Transformer World Models for Data-Efficient RL
por: Dedieu, Antoine, et al.
Publicado: (2025)

Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate
por: Luo, Fan-Ming, et al.
Publicado: (2024)

Integrating Domain Knowledge for handling Limited Data in Offline RL
por: Gangopadhyay, Briti, et al.
Publicado: (2024)

DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL
por: Jackermeier, Mathias, et al.
Publicado: (2024)

From Actions to Words: Towards Abstractive-Textual Policy Summarization in RL
por: Admoni, Sahar, et al.
Publicado: (2025)

Efficient RL Training for LLMs with Experience Replay
por: Arnal, Charles, et al.
Publicado: (2026)

FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning
por: Zhang, Xikai, et al.
Publicado: (2026)

Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards
por: Pavlenko, Kirill, et al.
Publicado: (2026)

Training RL Agents for Multi-Objective Network Defense Tasks
por: Molina-Markham, Andres, et al.
Publicado: (2025)

Adversarial Robustness of Discriminative Self-Supervised Learning in Vision
por: Çağatan, Ömer Veysel, et al.
Publicado: (2025)

BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL
por: Hung, Yu-Heng, et al.
Publicado: (2025)

Token-Efficient RL for LLM Reasoning
por: Lee, Alan, et al.
Publicado: (2025)

RL$^3$: Boosting Meta Reinforcement Learning via RL inside RL$^2$
por: Bhatia, Abhinav, et al.
Publicado: (2023)

Uniformly Safe RL with Objective Suppression for Multi-Constraint Safety-Critical Applications
por: Zhou, Zihan, et al.
Publicado: (2024)

Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RL
por: Kim, Sung-Hyun, et al.
Publicado: (2025)

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

QuRL: Efficient Reinforcement Learning with Quantized Rollout
por: Li, Yuhang, et al.
Publicado: (2026)

Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone
por: Mark, Max Sobol, et al.
Publicado: (2024)

RL2ML: Finite-Rollout Surrogate Objectives from Reinforcement Learning to Maximum Likelihood
por: Zheng, Yifu
Publicado: (2026)

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)

MindSpeed RL: Distributed Dataflow for Scalable and Efficient RL Training on Ascend NPU Cluster
por: Feng, Laingjun, et al.
Publicado: (2025)

Demonstration-Regularized RL
por: Tiapkin, Daniil, et al.
Publicado: (2023)

RL-Guided Data Selection for Language Model Finetuning
por: Jha, Animesh, et al.
Publicado: (2025)

SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training
por: Wang, Chen, et al.
Publicado: (2025)

When Are RL Hyperparameters Benign? A Study in Offline Goal-Conditioned RL
por: Töpperwien, Jan Malte, et al.
Publicado: (2026)

RL-GPT: Integrating Reinforcement Learning and Code-as-policy
por: Liu, Shaoteng, et al.
Publicado: (2024)

Learning-Zone Energy: Online Data Selection for Efficient RL Post-Training
por: Cui, Peng, et al.
Publicado: (2026)

UFO-RL: Uncertainty-Focused Optimization for Efficient Reinforcement Learning Data Selection
por: Zhao, Yang, et al.
Publicado: (2025)

CoScale-RL: Efficient Post-Training by Co-Scaling Data and Computation
por: Chen, Yutong, et al.
Publicado: (2026)

RL Token: Bootstrapping Online RL with Vision-Language-Action Models
por: Xu, Charles, et al.
Publicado: (2026)

BoreaRL: A Multi-Objective Reinforcement Learning Environment for Climate-Adaptive Boreal Forest Management
por: Dsouza, Kevin Bradley, et al.
Publicado: (2025)