Ignorance is Bliss: Robust Control via Information Gating

• URL: http://arxiv.org/abs/2303.06121v2
• Date: Fri, 8 Dec 2023 20:35:34 GMT
• Title: Ignorance is Bliss: Robust Control via Information Gating
• Authors: Manan Tomar, Riashat Islam, Matthew E. Taylor, Sergey Levine, Philip Bachman
• Abstract summary: 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.
• Score: 60.17644038829572
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Informational parsimony provides a useful inductive bias for learning representations that achieve better generalization by being robust to noise and spurious correlations. We propose \textit{information 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 \textit{InfoGating}. 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.

Related papers

• Meta-Learning Online Adaptation of Language Models [88.8947656843812]
  Large language models encode impressively broad world knowledge in their parameters. However, the knowledge in static language models falls out of date, limiting the model's effective "shelf life"
  arXiv  Detail & Related papers  (2023-05-24T11:56:20Z)
• FUNCK: Information Funnels and Bottlenecks for Invariant Representation Learning [7.804994311050265]
  We investigate a set of related information funnels and bottleneck problems that claim to learn invariant representations from the data. We propose a new element to this family of information-theoretic objectives: The Conditional Privacy Funnel with Side Information. Given the generally intractable objectives, we derive tractable approximations using amortized variational inference parameterized by neural networks.
  arXiv  Detail & Related papers  (2022-11-02T19:37:55Z)
• Denoised MDPs: Learning World Models Better Than the World Itself [94.74665254213588]
  This work categorizes information out in the wild into four types based on controllability and relation with reward, and formulates useful information as that which is both controllable and reward-relevant. Experiments on variants of DeepMind Control Suite and RoboDesk demonstrate superior performance of our denoised world model over using raw observations alone.
  arXiv  Detail & Related papers  (2022-06-30T17:59:49Z)
• Reasoning-Modulated Representations [85.08205744191078]
  We study a common setting where our task is not purely opaque. Our approach paves the way for a new class of data-efficient representation learning.
  arXiv  Detail & Related papers  (2021-07-19T13:57:13Z)
• Conditional Contrastive Learning: Removing Undesirable Information in Self-Supervised Representations [108.29288034509305]
  We develop conditional contrastive learning to remove undesirable information in self-supervised representations. We demonstrate empirically that our methods can successfully learn self-supervised representations for downstream tasks.
  arXiv  Detail & Related papers  (2021-06-05T10:51:26Z)
• Parrot: Data-Driven Behavioral Priors for Reinforcement Learning [79.32403825036792]
  We propose a method for pre-training behavioral priors that can capture complex input-output relationships observed in successful trials. We show how this learned prior can be used for rapidly learning new tasks without impeding the RL agent's ability to try out novel behaviors.
  arXiv  Detail & Related papers  (2020-11-19T18:47:40Z)
• Looking back to lower-level information in few-shot learning [4.873362301533825]
  We propose the utilization of lower-level, supporting information, namely the feature embeddings of the hidden neural network layers, to improve classification accuracy. Our experiments on two popular few-shot learning datasets, miniImageNet and tieredImageNet, show that our method can utilize the lower-level information in the network to improve state-of-the-art classification performance.
  arXiv  Detail & Related papers  (2020-05-27T20:32:13Z)
• Vector-Quantized Autoregressive Predictive Coding [31.4011465698136]
  We propose Vector-Quantized Autoregressive Predictive Coding (VQ-APC), a novel model that produces quantized representations. By studying a sequence of increasingly limited models, we reveal the constituents of the learned representations. We find that there exists a point where phonetic and speaker information are amplified to maximize a self-supervised objective.
  arXiv  Detail & Related papers  (2020-05-17T23:06:09Z)

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.