Related papers: The MAGICAL Benchmark for Robust Imitation

The MAGICAL Benchmark for Robust Imitation

URL: http://arxiv.org/abs/2011.00401v1
Date: Sun, 1 Nov 2020 02:04:16 GMT
Title: The MAGICAL Benchmark for Robust Imitation
Authors: Sam Toyer, Rohin Shah, Andrew Critch, Stuart Russell
Abstract summary: Imitation Learning (IL) algorithms are typically evaluated in the same environment that was used to create demonstrations. This paper presents the MAGICAL benchmark suite, which permits systematic evaluation of generalisation.
Score: 16.699877076711548
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Imitation Learning (IL) algorithms are typically evaluated in the same environment that was used to create demonstrations. This rewards precise reproduction of demonstrations in one particular environment, but provides little information about how robustly an algorithm can generalise the demonstrator's intent to substantially different deployment settings. This paper presents the MAGICAL benchmark suite, which permits systematic evaluation of generalisation by quantifying robustness to different kinds of distribution shift that an IL algorithm is likely to encounter in practice. Using the MAGICAL suite, we confirm that existing IL algorithms overfit significantly to the context in which demonstrations are provided. We also show that standard methods for reducing overfitting are effective at creating narrow perceptual invariances, but are not sufficient to enable transfer to contexts that require substantially different behaviour, which suggests that new approaches will be needed in order to robustly generalise demonstrator intent. Code and data for the MAGICAL suite is available at https://github.com/qxcv/magical/.

Related papers

A General Online Algorithm for Optimizing Complex Performance Metrics [5.726378955570775]
We introduce and analyze a general online algorithm that can be used in a straightforward way with a variety of complex performance metrics in binary, multi-class, and multi-label classification problems. The algorithm's update and prediction rules are appealingly simple and computationally efficient without the need to store any past data.
arXiv Detail & Related papers (2024-06-20T21:24:47Z)
Adaptive Experimentation at Scale: A Computational Framework for Flexible Batches [7.390918770007728]
Motivated by practical instances involving a handful of reallocations in which outcomes are measured in batches, we develop an adaptive-driven experimentation framework. Our main observation is that normal approximations, which are universal in statistical inference, can also guide the design of adaptive algorithms.
arXiv Detail & Related papers (2023-03-21T04:17:03Z)
Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning [146.11600461034746]
Method for unsupervised meta-learning, CACTUs, is a clustering-based approach with pseudo-labeling. This approach is model-agnostic and can be combined with supervised algorithms to learn from unlabeled data. We prove that the core reason for this is lack of a clustering-friendly property in the embedding space.
arXiv Detail & Related papers (2022-09-27T19:04:36Z)
Making Linear MDPs Practical via Contrastive Representation Learning [101.75885788118131]
It is common to address the curse of dimensionality in Markov decision processes (MDPs) by exploiting low-rank representations. We consider an alternative definition of linear MDPs that automatically ensures normalization while allowing efficient representation learning. We demonstrate superior performance over existing state-of-the-art model-based and model-free algorithms on several benchmarks.
arXiv Detail & Related papers (2022-07-14T18:18:02Z)
Adaptive Hierarchical Similarity Metric Learning with Noisy Labels [138.41576366096137]
We propose an Adaptive Hierarchical Similarity Metric Learning method. It considers two noise-insensitive information, textiti.e., class-wise divergence and sample-wise consistency. Our method achieves state-of-the-art performance compared with current deep metric learning approaches.
arXiv Detail & Related papers (2021-10-29T02:12:18Z)
The Benchmark Lottery [114.43978017484893]
"A benchmark lottery" describes the overall fragility of the machine learning benchmarking process. We show that the relative performance of algorithms may be altered significantly simply by choosing different benchmark tasks.
arXiv Detail & Related papers (2021-07-14T21:08:30Z)
How Fine-Tuning Allows for Effective Meta-Learning [50.17896588738377]
We present a theoretical framework for analyzing representations derived from a MAML-like algorithm. We provide risk bounds on the best predictor found by fine-tuning via gradient descent, demonstrating that the algorithm can provably leverage the shared structure. This separation result underscores the benefit of fine-tuning-based methods, such as MAML, over methods with "frozen representation" objectives in few-shot learning.
arXiv Detail & Related papers (2021-05-05T17:56:00Z)
CIMON: Towards High-quality Hash Codes [63.37321228830102]
We propose a new method named textbfComprehensive stextbfImilarity textbfMining and ctextbfOnsistency leartextbfNing (CIMON) First, we use global refinement and similarity statistical distribution to obtain reliable and smooth guidance. Second, both semantic and contrastive consistency learning are introduced to derive both disturb-invariant and discriminative hash codes.
arXiv Detail & Related papers (2020-10-15T14:47:14Z)
Study of Diffusion Normalized Least Mean M-estimate Algorithms [0.8749675983608171]
This work proposes diffusion normalized least mean M-estimate algorithm based on the modified Huber function. We analyze the transient, steady-state and stability behaviors of the algorithms in a unified framework. Simulations in various impulsive noise scenarios show that the proposed algorithms are superior to some existing diffusion algorithms.
arXiv Detail & Related papers (2020-04-20T00:28:41Z)

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