Related papers: Prior-Guided Diffusion Planning for Offline Reinfo…

Proximal Policy Optimization (PPO) is widely used in continuous control due to its robustness and stable training, yet it remains sample-inefficient in tasks with expensive interactions and high-dimensional action spaces. This paper…

Diffusion models are promising for joint trajectory prediction and controllable generation in autonomous driving, but they face challenges of inefficient inference steps and high computational demands. To tackle these challenges, we…

Offline Goal-Conditioned RL (GCRL) offers a feasible paradigm for learning general-purpose policies from diverse and multi-task offline datasets. Despite notable recent progress, the predominant offline GCRL methods, mainly model-free, face…

Classifier-free Guidance (CFG) is a widely used technique in modern diffusion models for enhancing sample quality and prompt adherence. However, through an empirical analysis on Gaussian mixture modeling with a closed-form solution, we…

Diffusion and flow matching policies offer expressive, multimodal action modeling, yet they are frequently unstable in online reinforcement learning (RL) due to intractable likelihoods and gradients propagating through long sampling chains.…

Conditional decision generation with diffusion models has shown powerful competitiveness in reinforcement learning (RL). Recent studies reveal the relation between energy-function-guidance diffusion models and constrained RL problems. The…

Generative diffusion models, famous for their performance in image generation, are popular in various cross-domain applications. However, their use in the communication community has been mostly limited to auxiliary tasks like data modeling…

Model-based reinforcement learning (MBRL) with autoregressive world models suffers from compounding errors, whereas diffusion world models mitigate this by generating trajectory segments jointly. However, existing diffusion guides are…

Diffusion models have been successfully applied in areas such as image, video, and audio generation. Recent works show their promise for sequential decision-making and dexterous manipulation, leveraging their ability to model complex action…

Recent progress in imitation learning has been enabled by policy architectures that scale to complex visuomotor tasks, multimodal distributions, and large datasets. However, these methods often rely on learning from large amount of expert…

Offline black-box optimization aims to maximize a black-box function using an offline dataset of designs and their measured properties. Two main approaches have emerged: the forward approach, which learns a mapping from input to its value,…

Safe Reinforcement Learning (RL) aims to find a policy that achieves high rewards while satisfying cost constraints. When learning from scratch, safe RL agents tend to be overly conservative, which impedes exploration and restrains the…

Offline reinforcement learning (RL) faces a critical challenge of overestimating the value of out-of-distribution (OOD) actions. Existing methods mitigate this issue by penalizing unseen samples, yet they fail to accurately identify OOD…

Diffusion-based motion planners are becoming popular due to their well-established performance improvements, stemming from sample diversity and the ease of incorporating new constraints directly during inference. However, a primary…

Diffusion policies trained via offline behavioral cloning have recently gained traction in robotic motion generation. While effective, these policies typically require a large number of trainable parameters. This model size affords powerful…

In offline reinforcement learning, weighted regression is a common method to ensure the learned policy stays close to the behavior policy and to prevent selecting out-of-sample actions. In this work, we show that due to the limited…

Diffusion models have achieved remarkable success in conditional image generation, yet their outputs often remain misaligned with human preferences. To address this, recent work has applied Direct Preference Optimization (DPO) to diffusion…

Legged locomotion demands controllers that are both robust and adaptable, while remaining compatible with task and safety considerations. However, model-free reinforcement learning (RL) methods often yield a fixed policy that can be…

Generative models have emerged as a powerful class of policies for offline reinforcement learning (RL) due to their ability to capture complex, multi-modal behaviors. However, existing methods face a stark trade-off: slow, iterative models…

Safe and effective motion planning is crucial for autonomous robots. Diffusion models excel at capturing complex agent interactions, a fundamental aspect of decision-making in dynamic environments. Recent studies have successfully applied…