arXiv:2607. 04153v1 Announce Type: cross Abstract: Vision-based deep reinforcement learning involves dealing with high-dimensional inputs of image information.
arXiv:2607. 00796v1 Announce Type: new Abstract: Visual Reinforcement Learning (VRL) has achieved considerable success in solving control tasks.
arXiv:2608. 05989v1 Announce Type: new Abstract: Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL).
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:2607. 00811v1 Announce Type: new Abstract: Unsupervised pre-training on large-scale datasets has demonstrated significant potential for improving the sample efficiency and performance of Reinforcement Learning (RL).
arXiv:2501. 14622v5 Announce Type: replace Abstract: Learning efficient representations for decision-making policies is a challenge in imitation learning (IL).
LoopVLA introduces a recurrent Vision‑Language‑Action architecture that learns to refine multimodal representations, predict actions, and estimate when further refinement is unnecessary. By iteratively applying a shared Transformer block and producing a sufficiency score at each step, it decouples refinement from fixed layer indices and aligns confidence scores with action quality through a self‑supervised objective. Experiments on LIBERO, LIBERO‑Plus, and VLA‑Arena demonstrate that LoopVLA reduces model parameters by 45% and boosts inference throughput up to 1.7× while matching or surpassing strong baselines in task success.
arXiv:2609.36645v1 Announce Type: cross Abstract: Future prediction is increasingly used to improve vision-language-action (VLA) policies, based on the premise that anticipating scene evolution encou...
arXiv:2606. 07687v1 Announce Type: cross Abstract: Video world models are increasingly used to provide predictive visual representations, yet it remains unclear which pretraining signals induce action-relevant structure in their latent spaces.
The paper proposes a method for learning task-relevant representations in deep reinforcement learning by maximizing rollout total correlation, which captures the correlation among all learned representations and actions across entire trajectories. It introduces two complementary lower bounds—one generative and one discriminative—along with chunk‑wise mini‑batching to improve this objective, and also proposes an intrinsic reward derived from the learned representation to enhance exploration. Experiments on challenging image‑based simulated control tasks demonstrate improved sample efficiency and robustness to white noise and natural video backgrounds compared to leading baselines.
The paper proposes a new architecture for Vision‑Language‑Action (VLA) models that improves sample efficiency by training a predictive world model on the vision encoder’s embedding space. It argues that these embeddings are action‑relevant and can be used to predict future states, addressing the lack of an explicit world model in current VLAs. The trained model can also support short‑term planning by sampling actions that lead to desired goal images.
The paper introduces Amortized Inpainting with Diffusion (AID), a method that keeps a pretrained diffusion backbone fixed and trains a small reusable guidance module offline for image inpainting. AID formulates the problem as deterministic guidance with a supervised terminal objective, derives an auxiliary Gaussian formulation to make it learnable, and proves that solving the randomized problem recovers the optimal deterministic guidance field. Experiments on AFHQv2, FFHQ, and ImageNet show that AID improves the quality–speed trade‑off over strong baselines while adding less than one percent trainable overhead.
arXiv:2606. 15768v1 Announce Type: cross Abstract: Vision-Language-Action models (VLAs) leverage large-scale vision-language pretraining for semantic robot control, but often lack explicit foresight into how robot actions change the scene.