arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.04790cs.LGcs.RO
收藏

通过条件近端策略优化实现扩散策略

Diffusion Policy through Conditional Proximal Policy Optimization

Southern University of Science and Technology, Shenzhen, China(南方科技大学);Hong Kong University of Science and Technology, Hongkong, China(香港科技大学);Zhejiang University-University of Illinois Urbana-Champaign Institute, Haining, China(浙江大学-伊利诺伊大学厄巴纳-香槟分校联合研究所)

Ben Liu, Shunpeng Yang, Hua Chen

AI总结:

本文提出了一种基于条件近端策略优化的高效方法,用于在在线强化学习中训练多模态扩散策略,解决了计算动作对数似然的难题,并在多个基准任务中取得优异性能。

摘要:

强化学习(RL)已被广泛应用于各种决策问题,如游戏和机器人领域。最近,扩散策略在建模多模态行为方面展现出强大潜力,相较于传统高斯策略,能够生成更加多样和灵活的动作。尽管已有多种尝试将RL与扩散结合,但关键挑战在于在扩散模型下计算动作对数似然的难度。这大大阻碍了扩散策略在在线强化学习中的直接应用。现有方法通常通过整个去噪过程计算或近似对数似然,这在内存和计算上都很低效。为克服这一挑战,我们提出了一种新颖且高效的训练方法,在在线设置下训练扩散策略,仅需评估一个简单的高斯概率。这是通过将策略迭代与扩散过程对齐实现的,这与以往工作有显著不同。此外,我们的公式可以自然处理熵正则化,这通常是将熵正则化融入扩散策略中的难点。实验表明,所提方法能够产生多模态策略行为,并在IsaacLab和MuJoCo Playground的各种基准任务中取得优越表现。

英文摘要:

Reinforcement learning (RL) has been extensively employed in a wide range of decision-making problems, such as games and robotics. Recently, diffusion policies have shown strong potential in modeling multi-modal behaviors, enabling more diverse and flexible action generation compared to the conventional Gaussian policy. Despite various attempts to combine RL with diffusion, a key challenge is the difficulty of computing action log-likelihood under the diffusion model. This greatly hinders the direct application of diffusion policies in on-policy reinforcement learning. Most existing methods calculate or approximate the log-likelihood through the entire denoising process in the diffusion model, which can be memory- and computationally inefficient. To overcome this challenge, we propose a novel and efficient method to train a diffusion policy in an on-policy setting that requires only evaluating a simple Gaussian probability. This is achieved by aligning the policy iteration with the diffusion process, which is a distinct paradigm compared to previous work. Moreover, our formulation can naturally handle entropy regularization, which is often difficult to incorporate into diffusion policies. Experiments demonstrate that the proposed method produces multimodal policy behaviors and achieves superior performance on a variety of benchmark tasks in both IsaacLab and MuJoCo Playground.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑