Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning

• URL: http://arxiv.org/abs/2412.05515v1
• Date: Sat, 07 Dec 2024 03:10:27 GMT
• Title: Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning
• Authors: Runhao Zeng, Dingjie Zhou, Qiwei Liang, Junlin Liu, Hui Li, Changxin Huang, Jianqiang Li, Xiping Hu, Fuchun Sun,
• Abstract summary: We introduce a new video2reward method, which directly generates reward functions from videos depicting the behaviors to be mimicked and learned. Our method surpasses the performance of state-of-the-art LLM-based reward generation methods by over 37.6% in terms of human normalized score.
• Score: 27.233232260388682
• License:
• Abstract: Learning behavior in legged robots presents a significant challenge due to its inherent instability and complex constraints. Recent research has proposed the use of a large language model (LLM) to generate reward functions in reinforcement learning, thereby replacing the need for manually designed rewards by experts. However, this approach, which relies on textual descriptions to define learning objectives, fails to achieve controllable and precise behavior learning with clear directionality. In this paper, we introduce a new video2reward method, which directly generates reward functions from videos depicting the behaviors to be mimicked and learned. Specifically, we first process videos containing the target behaviors, converting the motion information of individuals in the videos into keypoint trajectories represented as coordinates through a video2text transforming module. These trajectories are then fed into an LLM to generate the reward function, which in turn is used to train the policy. To enhance the quality of the reward function, we develop a video-assisted iterative reward refinement scheme that visually assesses the learned behaviors and provides textual feedback to the LLM. This feedback guides the LLM to continually refine the reward function, ultimately facilitating more efficient behavior learning. Experimental results on tasks involving bipedal and quadrupedal robot motion control demonstrate that our method surpasses the performance of state-of-the-art LLM-based reward generation methods by over 37.6% in terms of human normalized score. More importantly, by switching video inputs, we find our method can rapidly learn diverse motion behaviors such as walking and running.

Related papers

• Language-Model-Assisted Bi-Level Programming for Reward Learning from Internet Videos [48.2044649011213]
  We introduce a language-model-assisted bi-level programming framework that enables a reinforcement learning agent to learn its reward from internet videos. The framework includes two levels: an upper level where a vision-language model (VLM) provides feedback by comparing the learner's behavior with expert videos, and a lower level where a large language model (LLM) translates this feedback into reward updates. We validate the method for reward learning from YouTube videos, and the results have shown that the proposed method enables efficient reward design from expert videos of biological agents.
  arXiv  Detail & Related papers  (2024-10-11T22:31:39Z)
• RILe: Reinforced Imitation Learning [60.63173816209543]
  RILe is a framework that combines the strengths of imitation learning and inverse reinforcement learning to learn a dense reward function efficiently. Our framework produces high-performing policies in high-dimensional tasks where direct imitation fails to replicate complex behaviors.
  arXiv  Detail & Related papers  (2024-06-12T17:56:31Z)
• Learning Reward for Robot Skills Using Large Language Models via Self-Alignment [11.639973274337274]
  Large Language Models (LLM) contain valuable task-related knowledge that can potentially aid in the learning of reward functions. We propose a method to learn rewards more efficiently in the absence of humans.
  arXiv  Detail & Related papers  (2024-05-12T04:57:43Z)
• Any-point Trajectory Modeling for Policy Learning [64.23861308947852]
  We introduce Any-point Trajectory Modeling (ATM) to predict future trajectories of arbitrary points within a video frame. ATM outperforms strong video pre-training baselines by 80% on average. We show effective transfer learning of manipulation skills from human videos and videos from a different robot morphology.
  arXiv  Detail & Related papers  (2023-12-28T23:34:43Z)
• CLIP-Motion: Learning Reward Functions for Robotic Actions Using Consecutive Observations [1.03590082373586]
  This paper presents a novel method for learning reward functions for robotic motions by harnessing the power of a CLIP-based model. Our approach circumvents this challenge by capitalizing on CLIP's capability to process both state features and image inputs effectively.
  arXiv  Detail & Related papers  (2023-11-06T19:48:03Z)
• Learning Reward for Physical Skills using Large Language Model [5.795405764196473]
  Large Language Models contain valuable task-related knowledge that can aid in learning reward functions. We aim to extract task knowledge from LLMs using environment feedback to create efficient reward functions for physical skills.
  arXiv  Detail & Related papers  (2023-10-21T19:10:06Z)
• REST: REtrieve & Self-Train for generative action recognition [54.90704746573636]
  We propose to adapt a pre-trained generative Vision & Language (V&L) Foundation Model for video/action recognition. We show that direct fine-tuning of a generative model to produce action classes suffers from severe overfitting. We introduce REST, a training framework consisting of two key components.
  arXiv  Detail & Related papers  (2022-09-29T17:57:01Z)
• Motion Sensitive Contrastive Learning for Self-supervised Video Representation [34.854431881562576]
  Motion Sensitive Contrastive Learning (MSCL) injects the motion information captured by optical flows into RGB frames to strengthen feature learning. Local Motion Contrastive Learning (LMCL) with frame-level contrastive objectives across the two modalities. Flow Rotation Augmentation (FRA) to generate extra motion-shuffled negative samples and Motion Differential Sampling (MDS) to accurately screen training samples.
  arXiv  Detail & Related papers  (2022-08-12T04:06:56Z)
• Learning Object Manipulation Skills via Approximate State Estimation from Real Videos [47.958512470724926]
  Humans are adept at learning new tasks by watching a few instructional videos. On the other hand, robots that learn new actions either require a lot of effort through trial and error, or use expert demonstrations that are challenging to obtain. In this paper, we explore a method that facilitates learning object manipulation skills directly from videos.
  arXiv  Detail & Related papers  (2020-11-13T08:53:47Z)
• RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning [100.76672109782815]
  We study unsupervised video representation learning that seeks to learn both motion and appearance features from unlabeled video only. It is difficult to construct a suitable self-supervised task to well model both motion and appearance features. We propose a new way to perceive the playback speed and exploit the relative speed between two video clips as labels.
  arXiv  Detail & Related papers  (2020-10-27T16:42:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.