相关论文: Horizon Imagination: Efficient On-Policy Rollout i…

Memorization in large-scale text-to-image diffusion models poses significant security and intellectual property risks, enabling adversarial attribute extraction and the unauthorized reproduction of sensitive or proprietary features. While…

Robotic manipulation policies are commonly initialized through imitation learning, but their performance is limited by the scarcity and narrow coverage of expert data. Reinforcement learning can refine polices to alleviate this limitation,…

We present a hierarchical planning and control framework that enables an agent to perform various tasks and adapt to a new task flexibly. Rather than learning an individual policy for each particular task, the proposed framework, DISH,…

Diffusion-based visuomotor policies perform well in robotic manipulation, yet current methods still inherit image-generation-style decoders and multi-step sampling. We revisit this design from a frequency-domain perspective. Robot action…

In many real-world settings, agents must learn from an offline dataset gathered by some prior behavior policy. Such a setting naturally leads to distribution shift between the behavior policy and the target policy being trained - requiring…

World model based planning has significantly improved decision-making in complex environments by enabling agents to simulate future states and make informed choices. This computational burden is particularly restrictive in robotics, where…

Diffusion models have achieved remarkable progress in the field of image generation due to their outstanding capabilities. However, these models require substantial computing resources because of the multi-step denoising process during…

Humans can imagine goal states during planning and perform actions to match those goals. In this work, we propose Imagination Policy, a novel multi-task key-frame policy network for solving high-precision pick and place tasks. Instead of…

Diffusion Policy has shown great performance in robotic manipulation tasks under stochastic perturbations, due to its ability to model multimodal action distributions. Nonetheless, its reliance on a computationally expensive reverse-time…

Off-policy evaluation of sequential decision policies from observational data is necessary in applications of batch reinforcement learning such as education and healthcare. In such settings, however, unobserved variables confound observed…

Diffusion-based generative methods have shown promising potential for modeling trajectories from offline reinforcement learning (RL) datasets, and hierarchical diffusion has been introduced to mitigate variance accumulation and…

Reinforcement learning (RL) struggles to scale to large, combinatorial action spaces common in many real-world problems. This paper introduces a novel framework for training discrete diffusion models as highly effective policies in these…

We study continual offline reinforcement learning, a practical paradigm that facilitates forward transfer and mitigates catastrophic forgetting to tackle sequential offline tasks. We propose a dual generative replay framework that retains…

There is strong empirical evidence that the state-of-the-art diffusion modeling paradigm leads to models that memorize the training set, especially when the training set is small. Prior methods to mitigate the memorization problem often…

In this paper we propose an on-line policy iteration (PI) algorithm for finite-state infinite horizon discounted dynamic programming, whereby the policy improvement operation is done on-line, only for the states that are encountered during…

World models are a powerful tool for developing intelligent agents. By predicting the outcome of a sequence of actions, world models enable policies to be optimised via on-policy reinforcement learning (RL) using synthetic data, i.e. in "in…

We address the problem of generating long-horizon videos for robotic manipulation tasks. Text-to-video diffusion models have made significant progress in photorealism, language understanding, and motion generation but struggle with…

Offline Reinforcement Learning (RL) learns optimal policies from fixed datasets, training a policy once and deploying it at inference time without further refinement. Inspired by model predictive control (MPC), we introduce an inference…

Learning diverse policies for non-prehensile manipulation is essential for improving skill transfer and generalization to out-of-distribution scenarios. In this work, we enhance exploration through a two-fold approach within a hybrid…

High-resolution sinogram completion is critical for computed tomography reconstruction, as missing projections can introduce severe artifacts. While diffusion models provide strong generative priors for this task, their inference cost grows…