paper-with-me

홈 › Papers

Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion

2024-07-15 · Yongyuan Liang, Tingqiang Xu, Kaizhe Hu, Guangqi Jiang, Furong Huang, Huazhe Xu

Can we generate a control policy for an agent using just one demonstration of desired behaviors as a prompt, as effortlessly as creating an image from a textual description? In this paper, we present Make-An-Agent, a novel policy parameter generator that leverages the power of conditional diffusion models for behavior-to-policy generation. Guided by behavior embeddings that encode trajectory information, our policy generator synthesizes latent parameter representations, which can then be decoded into policy networks. Trained on policy network checkpoints and their corresponding trajectories, our generation model demonstrates remarkable versatility and scalability on multiple tasks and has a strong generalization ability on unseen tasks to output well-performed policies with only few-shot demonstrations as inputs. We showcase its efficacy and efficiency on various domains and tasks, including varying objectives, behaviors, and even across different robot manipulators. Beyond simulation, we directly deploy policies generated by Make-An-Agent onto real-world robots on locomotion tasks. Project page: https://cheryyunl.github.io/make-an-agent/

📄 PDF Abstract BibTeX arXiv:2407.10973

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning

2022-10-18 · Wei Qiu, Xiao Ma, Bo An, Svetlana Obraztsova 외

Despite the recent advancement in multi-agent reinforcement learning (MARL), the MARL agents easily overfit the training environment and perform poorly in the evaluation scenarios where other agents behave differently. O…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Offline Multi-agent Reinforcement Learning via Score Decomposition

2025-05-09 · Dan Qiao, Wenhao Li, Shanchao Yang, Hongyuan Zha 외

Offline cooperative multi-agent reinforcement learning (MARL) faces unique challenges due to distributional shifts, particularly stemming from the high dimensionality of joint action spaces and the presence of out-of-dis…

continuous-controlContinuous ControlMuJoCoMulti-agent Reinforcement Learning+2

Learning the Generalizable Manipulation Skills on Soft-body Tasks via Guided Self-attention Behavior Cloning Policy

2024-10-08 · Xuetao Li, Fang Gao, Jun Yu, Shaodong Li 외

Embodied AI represents a paradigm in AI research where artificial agents are situated within and interact with physical or virtual environments. Despite the recent progress in Embodied AI, it is still very challenging to…

Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation

2025-03-27 · Sicong Liu, Yang Shu, Chenjuan Guo, Bin Yang

Learning cooperative multi-agent policy from offline multi-task data that can generalize to unseen tasks with varying numbers of agents and targets is an attractive problem in many scenarios. Although aggregating general…

MuJoCoSMACSMAC+

Learning to design without prior data: Discovering generalizable design strategies using deep learning and tree search

2022-11-28 · Ayush Raina, Jonathan Cagan, Christopher McComb

Building an AI agent that can design on its own has been a goal since the 1980s. Recently, deep learning has shown the ability to learn from large-scale data, enabling significant advances in data-driven design. However,…

AI AgentSelf-LearningZero-shot Generalization