arXiv:2608. 05989v1 Announce Type: new Abstract: Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL).
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL). Recent dynamics-based representation learning methods have significantly improved the sample efficiency of model-free visual RL by learning dynamics-aware representations through auxiliary prediction performed either in latent space (self-prediction) or observation space (observation prediction).
arXiv:2608. 11605v1 Announce Type: new Abstract: World Action Models (WAMs) couple future visual prediction with robot action generation, enabling policies to model how the physical world evolves during interaction.
arXiv:2609.37250v1 Announce Type: cross Abstract: World-action models (WAMs) couple future visual-state prediction with action generation. By adapting video generators or image-editing models pretrai...
arXiv:2606. 12200v1 Announce Type: cross Abstract: We study policy representation learning from unlabeled multi-policy behavioral data.
The paper introduces the Dual-Latent World Model (Dual-WM), which separates local execution and long-range planning into distinct latent spaces and dynamics models. A new learning method, Long-Horizon Representation Learning with Weighted Rollout (LoRe), supervises predictions at both levels using exponential horizon weights. Experiments on five goal-conditioned visual control tasks show that Dual-WM improves success rates over strong baselines, especially at longer horizons.
arXiv:2607. 00796v1 Announce Type: new Abstract: Visual Reinforcement Learning (VRL) has achieved considerable success in solving control tasks.