Image de couverture de livre

Simulus: Combining Improvements in Sample-Efficient World Model Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Cohen, Lior, Wang, Kaixin, Kang, Bingyi, Gadot, Uri, Mannor, Shie
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Improving Token-Based World Models with Parallel Observation Prediction
par: Cohen, Lior, et autres
Publié: (2024)

Policy Gradient with Tree Search: Avoiding Local Optimas through Lookahead
par: Koren, Uri, et autres
Publié: (2025)

Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models
par: Cohen, Lior, et autres
Publié: (2026)

Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
par: Wang, Kaixin, et autres
Publié: (2023)

MinMaxMin $Q$-learning
par: Soffair, Nitsan, et autres
Publié: (2024)

Conservative DDPG -- Pessimistic RL without Ensemble
par: Soffair, Nitsan, et autres
Publié: (2024)

Sobolev Space Regularised Pre Density Models
par: Kozdoba, Mark, et autres
Publié: (2023)

Controlling False Discovery in Arbitrarily Structured Hypothesis Spaces via Reproducing Kernels
par: Perets, Binyamin, et autres
Publié: (2026)

Representation-Driven Reinforcement Learning
par: Nabati, Ofir, et autres
Publié: (2023)

Policy Optimized Text-to-Image Pipeline Design
par: Gadot, Uri, et autres
Publié: (2025)

Tree Search-Based Policy Optimization under Stochastic Execution Delay
par: Valensi, David, et autres
Publié: (2024)

RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression
par: Gadot, Uri, et autres
Publié: (2025)

SQT -- std $Q$-target
par: Soffair, Nitsan, et autres
Publié: (2024)

Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization
par: Du, Yihan, et autres
Publié: (2024)

Solving Non-Rectangular Reward-Robust MDPs via Frequency Regularization
par: Gadot, Uri, et autres
Publié: (2023)

RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation
par: Kwon, Jeongyeol, et autres
Publié: (2024)

Policy Gradient with Tree Expansion
par: Dalal, Gal, et autres
Publié: (2023)

VLM-Guided Experience Replay
par: Sharony, Elad, et autres
Publié: (2026)

Dual Formulation for Non-Rectangular Lp Robust Markov Decision Processes
par: Kumar, Navdeep, et autres
Publié: (2025)

Learning Multiple Initial Solutions to Optimization Problems
par: Sharony, Elad, et autres
Publié: (2024)

Optimal Sample Complexity for Single Time-Scale Actor-Critic with Momentum
par: Kumar, Navdeep, et autres
Publié: (2026)

Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization
par: Park, Ryan, et autres
Publié: (2024)

Efficient Fairness-Performance Pareto Front Computation
par: Kozdoba, Mark, et autres
Publié: (2024)

Implementing Reinforcement Learning Datacenter Congestion Control in NVIDIA NICs
par: Fuhrer, Benjamin, et autres
Publié: (2022)

BagStacking: An Integrated Ensemble Learning Approach for Freezing of Gait Detection in Parkinson's Disease
par: Cohen, Seffi, et autres
Publié: (2024)

FairTTTS: A Tree Test Time Simulation Method for Fairness-Aware Classification
par: Cohen-Inger, Nurit, et autres
Publié: (2025)

Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models
par: Zhang, Yang, et autres
Publié: (2024)

Representative Action Selection for Large Action Space: From Bandits to MDPs
par: Zhou, Quan, et autres
Publié: (2025)

DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution
par: Yue, Yang, et autres
Publié: (2024)

From Efficient Multimodal Models to World Models: A Survey
par: Mai, Xinji, et autres
Publié: (2024)

Dynamic Layer Tying for Parameter-Efficient Transformers
par: Hay, Tamir David, et autres
Publié: (2024)

Deep SPI: Safe Policy Improvement via World Models
par: Delgrange, Florent, et autres
Publié: (2025)

On the Provable Performance Guarantee of Efficient Reasoning Models
par: Zeng, Hao, et autres
Publié: (2025)

WIMLE: Uncertainty-Aware World Models with IMLE for Sample-Efficient Continuous Control
par: Aghabozorgi, Mehran, et autres
Publié: (2026)

RACER: Risk-Aware Calibrated Efficient Routing for Large Language Models
par: Hao, Sai, et autres
Publié: (2026)

SOE: Sample-Efficient Robot Policy Self-Improvement via On-Manifold Exploration
par: Jin, Yang, et autres
Publié: (2025)

Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model Training
par: Bhaskara, Vin, et autres
Publié: (2026)

Mutual Information Regularized Offline Reinforcement Learning
par: Ma, Xiao, et autres
Publié: (2022)

The Value of Mechanistic Priors in Sequential Decision Making
par: Shufaro, Itai, et autres
Publié: (2026)

World Modelling Improves Language Model Agents
par: Guo, Shangmin, et autres
Publié: (2025)