Problem Space Transformations for Out-of-Distribution Generalisation in Behavioural Cloning

• URL: http://arxiv.org/abs/2411.04056v2
• Date: Fri, 20 Jun 2025 14:56:44 GMT
• Title: Problem Space Transformations for Out-of-Distribution Generalisation in Behavioural Cloning
• Authors: Kiran Doshi, Marco Bagatella, Stelian Coros,
• Abstract summary: Behavioural cloning and neural networks have driven significant progress in robotic manipulation.<n>One of the remaining challenges is thus out-of-distribution (OOD) generalisation.<n>We show how transformations arising from characteristic properties of manipulation could be employed for its improvement.
• Score: 17.91476826271504
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The combination of behavioural cloning and neural networks has driven significant progress in robotic manipulation. As these algorithms may require a large number of demonstrations for each task of interest, they remain fundamentally inefficient in complex scenarios, in which finite datasets can hardly cover the state space. One of the remaining challenges is thus out-of-distribution (OOD) generalisation, i.e. the ability to predict correct actions for states with a low likelihood with respect to the state occupancy induced by the dataset. This issue is aggravated when the system to control is treated as a black-box, ignoring its physical properties. This work characterises widespread properties of robotic manipulation, specifically pose equivariance and locality. We investigate the effect of the choice of problem space on OOD performance of BC policies and how transformations arising from characteristic properties of manipulation could be employed for its improvement. We empirically demonstrate that these transformations allow behaviour cloning policies, using either standard MLP-based one-step action prediction or diffusion-based action-sequence prediction, to generalise better to OOD problem instances.

Related papers

• Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models [71.34520793462069]
  Unsupervised reinforcement learning (RL) aims at pre-training agents that can solve a wide range of downstream tasks in complex environments.<n>We introduce a novel algorithm regularizing unsupervised RL towards imitating trajectories from unlabeled behavior datasets.<n>We demonstrate the effectiveness of this new approach in a challenging humanoid control problem.
  arXiv  Detail & Related papers  (2025-04-15T10:41:11Z)
• Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy [56.424032454461695]
  We present Dita, a scalable framework that leverages Transformer architectures to directly denoise continuous action sequences.<n>Dita employs in-context conditioning -- enabling fine-grained alignment between denoised actions and raw visual tokens from historical observations.<n>Dita effectively integrates cross-embodiment datasets across diverse camera perspectives, observation scenes, tasks, and action spaces.
  arXiv  Detail & Related papers  (2025-03-25T15:19:56Z)
• Large-Scale Targeted Cause Discovery with Data-Driven Learning [66.86881771339145]
  We propose a novel machine learning approach for inferring causal variables of a target variable from observations. By employing a local-inference strategy, our approach scales with linear complexity in the number of variables, efficiently scaling up to thousands of variables. Empirical results demonstrate superior performance in identifying causal relationships within large-scale gene regulatory networks.
  arXiv  Detail & Related papers  (2024-08-29T02:21:11Z)
• Deep multitask neural networks for solving some stochastic optimal control problems [0.0]
  In this paper, we consider a class of optimal control problems and introduce an effective solution employing neural networks. To train our multitask neural network, we introduce a novel scheme that dynamically balances the learning across tasks. Through numerical experiments on real-world derivatives pricing problems, we prove that our method outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-01-23T17:20:48Z)
• D2NO: Efficient Handling of Heterogeneous Input Function Spaces with Distributed Deep Neural Operators [7.119066725173193]
  We propose a novel distributed approach to deal with input functions that exhibit heterogeneous properties. A central neural network is used to handle shared information across all output functions. We demonstrate that the corresponding neural network is a universal approximator of continuous nonlinear operators.
  arXiv  Detail & Related papers  (2023-10-29T03:29:59Z)
• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation [60.00649221656642]
  We study imitation learning policies in simulation and on a real robot language-conditioned manipulation task. We design a new simulated benchmark of 19 tasks with 11 factors of variation to facilitate more controlled evaluations of generalization.
  arXiv  Detail & Related papers  (2023-07-07T15:26:03Z)
• RObotic MAnipulation Network (ROMAN) $\unicode{x2013}$ Hybrid Hierarchical Learning for Solving Complex Sequential Tasks [70.69063219750952]
  We present a Hybrid Hierarchical Learning framework, the Robotic Manipulation Network (ROMAN) ROMAN achieves task versatility and robust failure recovery by integrating behavioural cloning, imitation learning, and reinforcement learning. Experimental results show that by orchestrating and activating these specialised manipulation experts, ROMAN generates correct sequential activations for accomplishing long sequences of sophisticated manipulation tasks.
  arXiv  Detail & Related papers  (2023-06-30T20:35:22Z)
• Permutation Equivariant Neural Functionals [92.0667671999604]
  This work studies the design of neural networks that can process the weights or gradients of other neural networks. We focus on the permutation symmetries that arise in the weights of deep feedforward networks because hidden layer neurons have no inherent order. In our experiments, we find that permutation equivariant neural functionals are effective on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-02-27T18:52:38Z)
• Score-based Causal Representation Learning with Interventions [54.735484409244386]
  This paper studies the causal representation learning problem when latent causal variables are observed indirectly. The objectives are: (i) recovering the unknown linear transformation (up to scaling) and (ii) determining the directed acyclic graph (DAG) underlying the latent variables.
  arXiv  Detail & Related papers  (2023-01-19T18:39:48Z)
• Modeling Uncertain Feature Representation for Domain Generalization [49.129544670700525]
  We show that our method consistently improves the network generalization ability on multiple vision tasks. Our methods are simple yet effective and can be readily integrated into networks without additional trainable parameters or loss constraints.
  arXiv  Detail & Related papers  (2023-01-16T14:25:02Z)
• NaturalAdversaries: Can Naturalistic Adversaries Be as Effective as Artificial Adversaries? [61.58261351116679]
  We introduce a two-stage adversarial example generation framework (NaturalAdversaries) for natural language understanding tasks. It is adaptable to both black-box and white-box adversarial attacks based on the level of access to the model parameters. Our results indicate these adversaries generalize across domains, and offer insights for future research on improving robustness of neural text classification models.
  arXiv  Detail & Related papers  (2022-11-08T16:37:34Z)
• Invariant Causal Mechanisms through Distribution Matching [86.07327840293894]
  In this work we provide a causal perspective and a new algorithm for learning invariant representations. Empirically we show that this algorithm works well on a diverse set of tasks and in particular we observe state-of-the-art performance on domain generalization.
  arXiv  Detail & Related papers  (2022-06-23T12:06:54Z)
• Out-of-distribution Generalization with Causal Invariant Transformations [17.18953986654873]
  In this work, we tackle the OOD problem without explicitly recovering the causal feature. Under the setting of invariant causal mechanism, we theoretically show that if all such transformations are available, then we can learn a minimax optimal model. Noticing that knowing a complete set of these causal invariant transformations may be impractical, we further show that it suffices to know only a subset of these transformations.
  arXiv  Detail & Related papers  (2022-03-22T08:04:38Z)
• Automatic Generation of Individual Fuzzy Cognitive Maps from Longitudinal Data [0.0]
  Fuzzy Cognitive Maps (FCMs) are computational models that represent how factors (nodes) change over discrete interactions. In this paper, we use Genetic Algorithms to create one FCM for each agent, thus providing the means to automatically create a virtual population with heterogeneous behaviors.
  arXiv  Detail & Related papers  (2022-02-14T22:11:58Z)
• Disentangling Generative Factors of Physical Fields Using Variational Autoencoders [0.0]
  This work explores the use of variational autoencoders (VAEs) for non-linear dimension reduction. A disentangled decomposition is interpretable and can be transferred to a variety of tasks including generative modeling.
  arXiv  Detail & Related papers  (2021-09-15T16:02:43Z)
• The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning [11.247894240593691]
  We build systems that feed each sensory input from the environment into distinct, but identical neural networks. We show that these sensory networks can be trained to integrate information received locally, and through communication via an attention mechanism, can collectively produce a globally coherent policy.
  arXiv  Detail & Related papers  (2021-09-07T05:12:50Z)
• Unsupervised Behaviour Discovery with Quality-Diversity Optimisation [1.0152838128195467]
  Quality-Diversity algorithms refer to a class of evolutionary algorithms designed to find a collection of diverse and high-performing solutions to a given problem. In robotics, such algorithms can be used for generating a collection of controllers covering most of the possible behaviours of a robot. In this paper, we introduce: Autonomous Robots Realising their Abilities, an algorithm that uses a dimensionality reduction technique to automatically learn behavioural descriptors.
  arXiv  Detail & Related papers  (2021-06-10T10:40:18Z)
• Multi-task Supervised Learning via Cross-learning [102.64082402388192]
  We consider a problem known as multi-task learning, consisting of fitting a set of regression functions intended for solving different tasks. In our novel formulation, we couple the parameters of these functions, so that they learn in their task specific domains while staying close to each other. This facilitates cross-fertilization in which data collected across different domains help improving the learning performance at each other task.
  arXiv  Detail & Related papers  (2020-10-24T21:35:57Z)
• Bias and Variance of Post-processing in Differential Privacy [53.29035917495491]
  Post-processing immunity is a fundamental property of differential privacy. It is often argued that post-processing may introduce bias and increase variance. This paper takes a first step towards understanding the properties of post-processing.
  arXiv  Detail & Related papers  (2020-10-09T02:12:54Z)
• A Class of Algorithms for General Instrumental Variable Models [29.558215059892206]
  Causal treatment effect estimation is a key problem that arises in a variety of real-world settings. We provide a method for causal effect bounding in continuous distributions.
  arXiv  Detail & Related papers  (2020-06-11T12:32:24Z)

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.