# Ignorance is Bliss: Robust Control via Information Gating

arXiv: https://arxiv.org/abs/2303.06121 · HTML: https://mlsanity.com/paper/2303.06121/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 47 references that are in the map.
- First posted on arXiv 10 Mar 2023.

## Builds on (most cited first, 30 of 37)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Variational Diffusion Models](https://mlsanity.com/paper/2107.00630/) (2021)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training](https://mlsanity.com/paper/2210.00030/) (2022)
- [Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning](https://mlsanity.com/paper/1910.11956/) (2019)
- [Masked Siamese Networks for Label-Efficient Learning](https://mlsanity.com/paper/2204.07141/) (2022)
- [Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning](https://mlsanity.com/paper/1803.11347/) (2018)
- [Unsupervised Learning for Physical Interaction through Video Prediction](https://mlsanity.com/paper/1605.07157/) (2016)
- [Information Dropout: Learning Optimal Representations Through Noisy Computation](https://mlsanity.com/paper/1611.01353/) (2016)
- [Deep Reinforcement and InfoMax Learning](https://mlsanity.com/paper/2006.07217/) (2020)
- [Adversarial Masking for Self-Supervised Learning](https://mlsanity.com/paper/2201.13100/) (2022)
- [Denoised MDPs: Learning World Models Better Than the World Itself](https://mlsanity.com/paper/2206.15477/) (2022)
- [Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations](https://mlsanity.com/paper/2206.04779/) (2022)
- [Learning Task Informed Abstractions](https://mlsanity.com/paper/2106.15612/) (2021)
- [Viewmaker Networks: Learning Views for Unsupervised Representation Learning](https://mlsanity.com/paper/2010.07432/) (2020)

## Built on by (most cited first, 10 of 10)

- [Learning Latent Dynamic Robust Representations for World Models](https://mlsanity.com/paper/2405.06263/) (2024)
- [An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records](https://mlsanity.com/paper/2406.08958/) (2024)
- [MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning](https://mlsanity.com/paper/2312.15339/) (2023)
- [Curb Your Attention: Causal Attention Gating for Robust Trajectory Prediction in Autonomous Driving](https://mlsanity.com/paper/2410.07191/) (2024)
- [Policy-shaped prediction: avoiding distractions in model-based reinforcement learning](https://mlsanity.com/paper/2412.05766/) (2024)
- [Learning Versatile Skills with Curriculum Masking](https://mlsanity.com/paper/2410.17744/) (2024)
- [TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning](https://mlsanity.com/paper/2605.12236/) (2026)
- [Unified Auto-Encoding with Masked Diffusion](https://mlsanity.com/paper/2406.17688/) (2024)
- [SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasets](https://mlsanity.com/paper/2406.09486/) (2024)
- [DeGuV: Depth-Guided Visual Reinforcement Learning for Generalization and Interpretability in Manipulation](https://mlsanity.com/paper/2509.04970/) (2025)

## Abstract (arXiv)

Informational parsimony provides a useful inductive bias for learning representations that achieve better generalization by being robust to noise and spurious correlations. We propose textitinformation gating as a way to learn parsimonious representations that identify the minimal information required for a task. When gating information, we can learn to reveal as little information as possible so that a task remains solvable, or hide as little information as possible so that a task becomes unsolvable. We gate information using a differentiable parameterization of the signal-to-noise ratio, which can be applied to arbitrary values in a network, e.g., erasing pixels at the input layer or activations in some intermediate layer. When gating at the input layer, our models learn which visual cues matter for a given task. When gating intermediate layers, our models learn which activations are needed for subsequent stages of computation. We call our approach textitInfoGating. We apply InfoGating to various objectives such as multi-step forward and inverse dynamics models, Q-learning, and behavior cloning, highlighting how InfoGating can naturally help in discarding information not relevant for control. Results show that learning to identify and use minimal information can improve generalization in downstream tasks. Policies based on InfoGating are considerably more robust to irrelevant visual features, leading to improved pretraining and finetuning of RL models.