Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning

doi:doi:10.57702/hcle5q6g

Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning

Diffusion models have demonstrated highly-expressive generative capabilities in vision and NLP. Recent studies in reinforcement learning (RL) have shown that diffusion models are also powerful in modeling complex policies or trajectories in offline datasets.

BibTex:

@dataset{Haoran_He_and_Chenjia_Bai_and_Kang_Xu_and_Zhuoran_Yang_and_Weinan_Zhang_and_Dong_Wang_and_Bin_Zhao_and_Xuelong_Li_2024,
    abstract = {Diffusion models have demonstrated highly-expressive generative capabilities in vision and NLP. Recent studies in reinforcement learning (RL) have shown that diffusion models are also powerful in modeling complex policies or trajectories in offline datasets.},
    author = {Haoran He and Chenjia Bai and Kang Xu and Zhuoran Yang and Weinan Zhang and Dong Wang and Bin Zhao and Xuelong Li},
    doi = {10.57702/hcle5q6g},
    institution = {No Organization},
    keyword = {'Data Synthesis', 'Diffusion Models', 'Multi-Task RL', 'Planning'},
    month = {dec},
    publisher = {TIB},
    title = {Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning},
    url = {https://service.tib.eu/ldmservice/dataset/diffusion-model-is-an-effective-planner-and-data-synthesizer-for-multi-task-reinforcement-learning},
    year = {2024}
}