# Addressing Sample Complexity in Visual Tasks Using HER and Hallucinatory GANs

arXiv: https://arxiv.org/abs/1901.11529 · HTML: https://mlsanity.com/paper/1901.11529/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2019.

## Built on by (most cited first, 6 of 6)

- [Semantic HELM: A Human-Readable Memory for Reinforcement Learning](https://mlsanity.com/paper/2306.09312/) (2023)
- [MHER: Model-based Hindsight Experience Replay](https://mlsanity.com/paper/2107.00306/) (2021)
- [Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks](https://mlsanity.com/paper/2110.02414/) (2021)
- [Visual Hindsight Self-Imitation Learning for Interactive Navigation](https://mlsanity.com/paper/2312.03446/) (2023)
- [The Role of Exploration for Task Transfer in Reinforcement Learning](https://mlsanity.com/paper/2210.06168/) (2022)
- [CLAMGen: Closed-Loop Arm Motion Generation via Multi-view Vision-Based RL](https://mlsanity.com/paper/2103.13267/) (2021)

## Abstract (arXiv)

Reinforcement Learning (RL) algorithms typically require millions of environment interactions to learn successful policies in sparse reward settings. Hindsight Experience Replay (HER) was introduced as a technique to increase sample efficiency by reimagining unsuccessful trajectories as successful ones by altering the originally intended goals. However, it cannot be directly applied to visual environments where goal states are often characterized by the presence of distinct visual features. In this work, we show how visual trajectories can be hallucinated to appear successful by altering agent observations using a generative model trained on relatively few snapshots of the goal. We then use this model in combination with HER to train RL agents in visual settings. We validate our approach on 3D navigation tasks and a simulated robotics application and show marked improvement over baselines derived from previous work.