# Perceptual Values from Observation

arXiv: https://arxiv.org/abs/1905.07861 · HTML: https://mlsanity.com/paper/1905.07861/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2019.

## Built on by (most cited first, 11 of 11)

- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation](https://mlsanity.com/paper/2401.02117/) (2024)
- [MimicPlay: Long-Horizon Imitation Learning by Watching Human Play](https://mlsanity.com/paper/2302.12422/) (2023)
- [Learning Generalizable Robotic Reward Functions from "In-The-Wild" Human Videos](https://mlsanity.com/paper/2103.16817/) (2021)
- [Reinforcement Learning from Passive Data via Latent Intentions](https://mlsanity.com/paper/2304.04782/) (2023)
- [Towards Generalist Robot Learning from Internet Video: A Survey](https://mlsanity.com/paper/2404.19664/) (2024)
- [Surgical Robot Transformer (SRT): Imitation Learning for Surgical Tasks](https://mlsanity.com/paper/2407.12998/) (2024)
- [Learning Video-Conditioned Policies for Unseen Manipulation Tasks](https://mlsanity.com/paper/2305.06289/) (2023)
- [Learning Value Functions from Undirected State-only Experience](https://mlsanity.com/paper/2204.12458/) (2022)
- [VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions](https://mlsanity.com/paper/2410.20927/) (2024)
- [Chain-of-Modality: Learning Manipulation Programs from Multimodal Human Videos with Vision-Language-Models](https://mlsanity.com/paper/2504.13351/) (2025)

## Abstract (arXiv)

Imitation by observation is an approach for learning from expert demonstrations that lack action information, such as videos. Recent approaches to this problem can be placed into two broad categories: training dynamics models that aim to predict the actions taken between states, and learning rewards or features for computing them for Reinforcement Learning (RL). In this paper, we introduce a novel approach that learns values, rather than rewards, directly from observations. We show that by using values, we can significantly speed up RL by removing the need to bootstrap action-values, as compared to sparse-reward specifications.