Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion
Abstract
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.
Community
Make-An-Agent synthesizes policy network parameters using agents' trajectories as prompts. Train once, use everywhere.
Project: https://cheryyunl.github.io/make-an-agent/
Code: https://github.com/cheryyunl/Make-An-Agent
Dataset and models: https://huggingface.co/cheryyunl/Make-An-Agent
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning (2024)
- Text-Aware Diffusion for Policy Learning (2024)
- Diffusion-Reward Adversarial Imitation Learning (2024)
- BAKU: An Efficient Transformer for Multi-Task Policy Learning (2024)
- Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning (2024)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 1
Datasets citing this paper 1
Spaces citing this paper 0
No Space linking this paper