Imagen de Portada

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Kobayashi, Taisuke
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

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

Best-of-Tails: Bridging Optimism and Pessimism in Inference-Time Alignment
por: Hsu, Hsiang, et al.
Publicado: (2026)

Consolidated Adaptive T-soft Update for Deep Reinforcement Learning
por: Kobayashi, Taisuke
Publicado: (2022)

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

Intentionally-underestimated Value Function at Terminal State for Temporal-difference Learning with Mis-designed Reward
por: Kobayashi, Taisuke
Publicado: (2023)

CubeDAgger: Interactive Imitation Learning for Dynamic Systems with Efficient yet Low-risk Interaction
por: Kobayashi, Taisuke
Publicado: (2025)

Revisiting Experience Replayable Conditions
por: Kobayashi, Taisuke
Publicado: (2024)

Flexible Empowerment at Reasoning with Extended Best-of-N Sampling
por: Kobayashi, Taisuke
Publicado: (2026)

Pseudo-Quantized Actor-Critic Algorithm for Robustness to Noisy Temporal Difference Error
por: Kobayashi, Taisuke
Publicado: (2026)

Improvements of Dark Experience Replay and Reservoir Sampling towards Better Balance between Consolidation and Plasticity
por: Kobayashi, Taisuke
Publicado: (2025)

Minimax Optimal Reinforcement Learning with Quasi-Optimism
por: Lee, Harin, et al.
Publicado: (2025)

Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Sampling
por: Aouali, Imad, et al.
Publicado: (2024)

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

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

Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning
por: Zhang, Chi, et al.
Publicado: (2025)

On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning
por: Mhaisen, Naram, et al.
Publicado: (2025)

Design of Restricted Normalizing Flow towards Arbitrary Stochastic Policy with Computational Efficiency
por: Kobayashi, Taisuke, et al.
Publicado: (2024)

Variational Adaptive Noise and Dropout towards Stable Recurrent Neural Networks
por: Kobayashi, Taisuke, et al.
Publicado: (2025)

Towards Autonomous Driving of Personal Mobility with Small and Noisy Dataset using Tsallis-statistics-based Behavioral Cloning
por: Kobayashi, Taisuke, et al.
Publicado: (2021)

Optimism as Risk-Seeking in Multi-Agent Reinforcement Learning
por: Zhang, Runyu, et al.
Publicado: (2025)

Distributional Reinforcement Learning with Regularized Wasserstein Loss
por: Sun, Ke, et al.
Publicado: (2022)

Optimism Without Regularization: Constant Regret in Zero-Sum Games
por: Lazarsfeld, John, et al.
Publicado: (2025)

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

P-DROP: Poisson-Based Dropout for Graph Neural Networks
por: Yun, Hyunsik
Publicado: (2025)

Convergence Theorems for Entropy-Regularized and Distributional Reinforcement Learning
por: Jhaveri, Yash, 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 in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes
por: Lu, Miao, et al.
Publicado: (2022)

DROP: Poison Dilution via Knowledge Distillation for Federated Learning
por: Syros, Georgios, et al.
Publicado: (2025)

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

From Curiosity to Caution: Mitigating Reward Hacking for Best-of-N with Pessimism
por: Yu, Zhuohao, et al.
Publicado: (2026)

From Robotics to Sepsis Treatment: Offline RL via Geometric Pessimism
por: Wanjari, Sarthak
Publicado: (2026)

Directional Optimism for Safe Linear Bandits
por: Hutchinson, Spencer, et al.
Publicado: (2023)

Federated Distributional Reinforcement Learning with Distributional Critic Regularization
por: Millard, David, et al.
Publicado: (2026)

Online (Non-)Convex Learning via Tempered Optimism
por: Haddouche, Maxime, et al.
Publicado: (2023)

Escaping Offline Pessimism: Vector-Field Reward Shaping for Safe Frontier Exploration
por: Roknilamouki, Amirhossein, et al.
Publicado: (2026)

Beyond Optimism: Exploration With Partially Observable Rewards
por: Parisi, Simone, et al.
Publicado: (2024)

Weber-Fechner Law in Temporal Difference learning derived from Control as Inference
por: Takahashi, Keiichiro, et al.
Publicado: (2024)

Revisiting Optimism and Model Complexity in the Wake of Overparameterized Machine Learning
por: Patil, Pratik, et al.
Publicado: (2024)

Ancestral Reinforcement Learning: Unifying Zeroth-Order Optimization and Genetic Algorithms for Reinforcement Learning
por: Nakashima, So, et al.
Publicado: (2024)