Imagen de Portada

Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Chi, Jia, Ziying, Atia, George K., He, Sihong, Wang, Yue
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CADENT: Gated Hybrid Distillation for Sample-Efficient Transfer in Reinforcement Learning
por: Alinejad, Mahyar, et al.
Publicado: (2026)

Provably Sample-Efficient Robust Reinforcement Learning with Average Reward
por: Roch, Zachary, et al.
Publicado: (2025)

Online Robust Reinforcement Learning with General Function Approximation
por: Ghosh, Debamita, et al.
Publicado: (2025)

ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning
por: Ghosh, Debamita, et al.
Publicado: (2025)

Robust Transfer Learning with Side Information
por: Awad, Akram S., et al.
Publicado: (2026)

The Virtues of Pessimism in Inverse Reinforcement Learning
por: Wu, David, et al.
Publicado: (2024)

RLAF: Reinforcement Learning from Automaton Feedback
por: Alinejad, Mahyar, et al.
Publicado: (2025)

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning
por: Kobayashi, Taisuke
Publicado: (2024)

Sample-Efficient Distributionally Robust Multi-Agent Reinforcement Learning via Online Interaction
por: Farhat, Zain Ulabedeen, et al.
Publicado: (2025)

Bayesian Inverse Reinforcement Learning for Non-Markovian Rewards
por: Topper, Noah, et al.
Publicado: (2024)

Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning
por: Zhang, Dake, et al.
Publicado: (2024)

A Unified Framework for Zero-Shot Reinforcement Learning
por: Di Ventura, Jacopo, et al.
Publicado: (2025)

Towards Robust Zero-Shot Reinforcement Learning
por: Zheng, Kexin, et al.
Publicado: (2025)

Automaton Distillation: Neuro-Symbolic Transfer Learning for Deep Reinforcement Learning
por: Singireddy, Suraj, et al.
Publicado: (2023)

Constrained Reinforcement Learning Under Model Mismatch
por: Sun, Zhongchang, et al.
Publicado: (2024)

Zero-Shot Policy Transfer in Reinforcement Learning using Buckingham's Pi Theorem
por: Pascoa, Francisco, et al.
Publicado: (2025)

On Zero-Shot Reinforcement Learning
por: Jeen, Scott
Publicado: (2025)

DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design
por: Garcin, Samuel, et al.
Publicado: (2024)

Beyond Pessimism: Offline Learning in KL-regularized Games
por: Zhang, Yuheng, et al.
Publicado: (2026)

Zero-Shot Reinforcement Learning via Function Encoders
por: Ingebrand, Tyler, et al.
Publicado: (2024)

Improved Regret Bound for Safe Reinforcement Learning via Tighter Cost Pessimism and Reward Optimism
por: Yu, Kihyun, et al.
Publicado: (2024)

Efficient Reinforcement Learning for Zero-Shot Coordination in Evolving Games
por: Hui, Bingyu, et al.
Publicado: (2025)

Tackling the Zero-Shot Reinforcement Learning Loss Directly
por: Ollivier, Yann
Publicado: (2025)

Provable Zero-Shot Generalization in Offline Reinforcement Learning
por: Wang, Zhiyong, et al.
Publicado: (2025)

Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments
por: Wang, Han, et al.
Publicado: (2024)

Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games
por: Lu, Runyu, et al.
Publicado: (2025)

Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts
por: Zhang, Di, et al.
Publicado: (2025)

Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer
por: Gu, Xinyang, et al.
Publicado: (2024)

Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes
por: Lu, Miao, et al.
Publicado: (2022)

Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment
por: Trivedi, Prashant, et al.
Publicado: (2025)

A Tale of Two Cities: Pessimism and Opportunism in Offline Dynamic Pricing
por: Bian, Zeyu, et al.
Publicado: (2024)

Zero-Shot Reinforcement Learning Under Partial Observability
por: Jeen, Scott, et al.
Publicado: (2025)

TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning
por: Bagatella, Marco, et al.
Publicado: (2025)

Mitigating Preference Hacking in Policy Optimization with Pessimism
por: Gupta, Dhawal, et al.
Publicado: (2025)

Quantile Geometry Regularization for Distributional Reinforcement Learning
por: Zhang, Zhaofan, et al.
Publicado: (2026)

Pessimism-Free Offline Learning in General-Sum Games via KL Regularization
por: Chen, Claire, et al.
Publicado: (2026)

From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detection
por: Liu, Yixin, et al.
Publicado: (2026)

Zero-Shot Reinforcement Learning from Low Quality Data
por: Jeen, Scott, et al.
Publicado: (2023)

Towards Zero-Shot Task-Generalizable Learning on fMRI
por: Wang, Jiyao, et al.
Publicado: (2025)

Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning
por: Chen, Rufeng, et al.
Publicado: (2026)