arXiv Machine Learning
In-Distribution Imagination for Model-Based Offline Reinforcement Learning
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 17
RENEW: Towards Learning World Models and Repairing Model Exploitation from Preferences
arXiv:2607. 14180v1 Announce Type: cross Abstract: World models are widely used in offline reinforcement learning (RL) to improve sample efficiency and generate experience beyond a fixed dataset.
arXiv Machine Learning
Aug 27
Bayesian Flow Networks for Offline Trajectory Planning
The paper introduces Bayesian Flow Networks for Offline Trajectory Planning (BFN-RL), a generative modeling framework that unifies discrete and continuous trajectory synthesis for offline reinforcement learning. Unlike prior diffusion models that rely on Gaussian noise, BFN-RL iteratively updates distribution parameters, enabling a categorical planner to produce future state sequences and an inverse-dynamics model to translate these states into actions. Experiments demonstrate that BFN-RL effectively generates trajectories in both discrete planning and continuous control tasks, highlighting its versatility across data modalities.
arXiv AI
Jun 18
Robust Regularized Policy Iteration under Transition Uncertainty
arXiv:2603. 09344v3 Announce Type: replace Abstract: Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift.
arXiv AI
Jul 24
Expert Behavior Prior Reinforcement Learning
arXiv:2607. 21302v1 Announce Type: new Abstract: Behavior prior reinforcement learning (BPRL) has emerged as a promising paradigm to improve sample efficiency in online reinforcement learning (RL) by leveraging policy priors derived from offline demonstrations.
arXiv AI
Jul 13
Shortcut Trajectory Planning for Efficient Offline Reinforcement Learning
arXiv:2607. 09336v1 Announce Type: cross Abstract: Diffusion-based trajectory planners have shown strong performance in offline reinforcement learning, but their iterative denoising process often incurs high inference cost.
arXiv AI
Jun 12
WOMBET: World Model-Based Experience Transfer for Robust and Sample-efficient Reinforcement Learning
arXiv:2604. 08958v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) in robotics is often limited by the cost and risk of data collection, motivating experience transfer from a source task to a target task.