Related papers: BiTrajDiff: Bidirectional Trajectory Generation wi…
Mastering deep reinforcement learning (DRL) proves challenging in tasks featuring scant rewards. These limited rewards merely signify whether the task is partially or entirely accomplished, necessitating various exploration actions before…
Diffusion models (DMs) have recently demonstrated remarkable generation capability. However, their training generally requires huge computational resources and large-scale datasets. To solve these, recent studies empower DMs with the…
Off-dynamics reinforcement learning (RL), where training and deployment transition dynamics are different, can be formulated as learning in a robust Markov decision process (RMDP) where uncertainties in transition dynamics are imposed.…
Reinforcement learning (RL) has achieved remarkable success in a wide range of sequential decision-making problems. Recent diffusion-based policies further improve RL by modeling complex, high-dimensional action distributions. However,…
In offline Imitation Learning (IL), one of the main challenges is the \textit{covariate shift} between the expert observations and the actual distribution encountered by the agent, because it is difficult to determine what action an agent…
We introduce Diffusion Active Learning, a novel approach that combines generative diffusion modeling with data-driven sequential experimental design to adaptively acquire data for inverse problems. Although broadly applicable, we focus on…
In this paper, we introduce a novel approach for autonomous driving trajectory generation by harnessing the complementary strengths of diffusion probabilistic models (a.k.a., diffusion models) and transformers. Our proposed framework,…
Diffusion models are the mainstream approach for time series generation tasks. However, existing diffusion models for time series generation require retraining the entire framework to introduce specific conditional guidance. There also…
Diffusion Transformer (DiT), an emerging diffusion model for visual generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs primarily stem from the…
This work introduces TrajDiffuser, a compositional diffusion-based flexible and concurrent trajectory generator for 6 degrees of freedom powered descent guidance. TrajDiffuser is a statistical model that learns the multi-modal distributions…
Diffusion models excel at generating high-quality, diverse images but suffer from training data memorization, raising critical privacy and safety concerns. Data unlearning has emerged to mitigate this issue by removing the influence of…
Diffusion planners have shown promise in handling long-horizon and sparse-reward tasks due to the non-autoregressive plan generation. However, their inherent stochastic risk of generating infeasible trajectories presents significant…
Many reinforcement learning (RL) tasks have discrete action spaces, but most generative policy methods based on diffusion and flow matching are designed for continuous control. Meanwhile, generative policies usually rely heavily on offline…
Offline preference-based reinforcement learning (PbRL) mitigates the need for reward definition, aligning with human preferences via preference-driven reward feedback without interacting with the environment. However, trajectory-wise…
Offline reinforcement learning (RL) aims to learn a policy using only pre-collected and fixed data. Although avoiding the time-consuming online interactions in RL, it poses challenges for out-of-distribution (OOD) state actions and often…
Constrained policy search (CPS) is a fundamental problem in offline reinforcement learning, which is generally solved by advantage weighted regression (AWR). However, previous methods may still encounter out-of-distribution actions due to…
Offline decision-making via diffusion models often produces trajectories that are misaligned with system dynamics, limiting their reliability for control. We propose Model Predictive Diffuser (MPDiffuser), a compositional diffusion…
Reinforcement learning (RL) can be formulated as a sequence modeling problem, where models predict future actions based on historical state-action-reward sequences. Current approaches typically require long trajectory sequences to model the…
Reinforcement Learning (RL) has proven highly effective in addressing complex control and decision-making tasks. However, in most traditional RL algorithms, the policy is typically parameterized as a diagonal Gaussian distribution, which…
Offline-to-online deployment of reinforcement-learning (RL) agents must bridge two gaps: (1) the sim-to-real gap, where real systems add latency and other imperfections not present in simulation, and (2) the interaction gap, where policies…