Papers

• Arxiv

  • Enhancing Memory and Imagination Consistency in Diffusion-based World Models via Linear-Time Sequence Modeling
  • IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies
  • Synthetic Experience Replay
  • Value function estimation using conditional diffusion models for control
  • World Models via Policy-Guided Trajectory Diffusion
  • Diffusion Models for Reinforcement Learning: A Survey
  • Boosting Continuous Control with Consistency Policy
  • DiffCPS: Diffusion Model based Constrained Policy Search for Offline Reinforcement Learning
  • MADiff: Offline Multi-agent Learning with Diffusion Models
  • Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement Learning
  • Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
  • Diffusion-based Generation, Optimization, and Planning in 3D Scenes
  • ScanNet - liu/GenDexGrasp), [PROX](https://prox.is.tue.mpg.de/index.html)
  • Goal-Conditioned Imitation Learning using Score-based Diffusion Policies
  • official
  • official
  • Learning to Reach Goals via Diffusion
  • AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
  • Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model
  • NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration
  • IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies
  • To the Noise and Back: Diffusion for Shared Autonomy
  • PlayFusion: Skill Acquisition via Diffusion from Language-Annotated Play
  • XSkill: Cross Embodiment Skill Discovery
  • Diffusion Co-Policy for Synergistic Human-Robot Collaborative Tasks
  • GenAug: Retargeting behaviors to unseen situations via Generative Augmentation
  • Scaling Robot Learning with Semantically Imagined Experience
  • Synthetic Experience Replay
  • Value function estimation using conditional diffusion models for control
  • Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning
  • Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimization
  • 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
  • Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning

• NeurIPS 2023

  • Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping
  • IsaacGym
  • Efficient Diffusion Policies for Offline Reinforcement Learning
  • Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning
  • Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping

• ICML 2023

  • Optimizing DDPM Sampling with Shortcut Fine-Tuning
  • MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL
  • Hierarchical diffusion for offline decision making
  • Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning

• ICLR 2023

  • Is Conditional Generative Modeling all you need for Decision-Making?
  • official
  • Imitating Human Behaviour with Diffusion Models
  • Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling

• ICRA 2023

  • Guided Conditional Diffusion for Controllable Traffic Simulation

• NeurIPS 2022

  • TarGF: Learning Target Gradient Field to Rearrange Objects without Explicit Goal Specification
  • Room Rearrangement
  • Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning

• ICML 2022

  • Planning with Diffusion for Flexible Behavior Synthesis

• CVPR 2024

  • official
  • Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation

• ICLR 2024

  • Efficient Planning with Latent Diffusion
  • DMBP: Diffusion model based predictor for robust offline reinforcement learning against state observation perturbations
  • Flow to Better: Offline Preference-based Reinforcement Learning via Preferred Trajectory Generation
  • Score Regularized Policy Optimization through Diffusion Behavior
  • Simple Hierarchical Planning with Diffusion
  • Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion
  • NuScenes
  • AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
  • official
  • Training Diffusion Models with Reinforcement Learning
  • Reasoning with Latent Diffusion in Offline Reinforcement Learning
  • Training Diffusion Models with Reinforcement Learning