Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Models

• URL: http://arxiv.org/abs/2404.18896v2
• Date: Wed, 23 Apr 2025 19:11:30 GMT
• Title: Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Models
• Authors: Xingyuan Zhang, Philip Becker-Ehmck, Patrick van der Smagt, Maximilian Karl,
• Abstract summary: This study identifies two primary obstacles: the Embodiment Knowledge Barrier (EKB) and the Demonstration Knowledge Barrier (DKB)<n>The EKB emerges due to the pretrained models' limitations in handling novel observations, which leads to inaccurate action inference.<n>The DKB stems from the reliance on limited demonstration datasets, restricting the model's adaptability across diverse scenarios.<n>We propose separate solutions to overcome each barrier and apply them to Action Inference by Maximising Evidence (AIME)
• Score: 8.77288940968713
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pretraining and finetuning models has become increasingly popular in decision-making. But there are still serious impediments in Imitation Learning from Observation (ILfO) with pretrained models. This study identifies two primary obstacles: the Embodiment Knowledge Barrier (EKB) and the Demonstration Knowledge Barrier (DKB). The EKB emerges due to the pretrained models' limitations in handling novel observations, which leads to inaccurate action inference. Conversely, the DKB stems from the reliance on limited demonstration datasets, restricting the model's adaptability across diverse scenarios. We propose separate solutions to overcome each barrier and apply them to Action Inference by Maximising Evidence (AIME), a state-of-the-art algorithm. This new algorithm, AIME-NoB, integrates online interactions and a data-driven regulariser to mitigate the EKB. Additionally, it uses a surrogate reward function to broaden the policy's supported states, addressing the DKB. Our experiments on vision-based control tasks from the DeepMind Control Suite and MetaWorld benchmarks show that AIME-NoB significantly improves sample efficiency and converged performance, presenting a robust framework for overcoming the challenges in ILfO with pretrained models. Code available at https://github.com/IcarusWizard/AIME-NoB.

Related papers

• Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning [93.58897637077001]
  This paper tries to learn and understand underlying semantic variations from distracting videos via offline-to-online latent distillation and flexible disentanglement constraints. We pretrain the action-free video prediction model offline with disentanglement regularization to extract semantic knowledge from distracting videos. For finetuning in the online environment, we exploit the knowledge from the pretrained model and introduce a disentanglement constraint to the world model.
  arXiv  Detail & Related papers  (2025-03-11T13:50:22Z)
• ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning [90.41852663775086]
  ACT-JEPA is a novel architecture that integrates imitation learning and self-supervised learning. We train a policy to predict action sequences and abstract observation sequences. Our experiments show that ACT-JEPA improves the quality of representations by learning temporal environment dynamics.
  arXiv  Detail & Related papers  (2025-01-24T16:41:41Z)
• Meta-Learning for Physically-Constrained Neural System Identification [9.417562391585076]
  We present a gradient-based meta-learning framework for rapid adaptation of neural state-space models (NSSMs) for black-box system identification. We show that the meta-learned models result in improved downstream performance in model-based state estimation in indoor localization and energy systems.
  arXiv  Detail & Related papers  (2025-01-10T18:46:28Z)
• Verifying Machine Unlearning with Explainable AI [46.7583989202789]
  We investigate the effectiveness of Explainable AI (XAI) in verifying Machine Unlearning (MU) within context of harbor front monitoring. Our proof-of-concept introduces attribution feature as an innovative verification step for MU, expanding beyond traditional metrics. We propose two novel XAI-based metrics, Heatmap Coverage (HC) and Attention Shift (AS) to evaluate the effectiveness of these methods.
  arXiv  Detail & Related papers  (2024-11-20T13:57:32Z)
• Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration [74.09687562334682]
  We introduce a novel training data attribution method called Debias and Denoise Attribution (DDA) Our method significantly outperforms existing approaches, achieving an averaged AUC of 91.64%. DDA exhibits strong generality and scalability across various sources and different-scale models like LLaMA2, QWEN2, and Mistral.
  arXiv  Detail & Related papers  (2024-10-02T07:14:26Z)
• Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance [61.06245197347139]
  We propose a novel approach to explain the behavior of a black-box model under feature shifts. We refer to our method that combines concepts from Optimal Transport and Shapley Values as Explanatory Performance Estimation.
  arXiv  Detail & Related papers  (2024-08-24T18:28:19Z)
• Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models [19.015202590038996]
  We design Dynamic Unlearning Attack (DUA), a dynamic and automated framework to attack unlearned models. We propose Latent Adrial Unlearning (LAU), a universal framework that effectively enhances the robustness of the unlearned process. We demonstrate that LAU improves unlearning effectiveness by over $53.5%$, cause only less than a $11.6%$ reduction in neighboring knowledge, and have almost no impact on the model's general capabilities.
  arXiv  Detail & Related papers  (2024-08-20T09:36:04Z)
• Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models [79.28821338925947]
  Domain-Class Incremental Learning is a realistic but challenging continual learning scenario. To handle these diverse tasks, pre-trained Vision-Language Models (VLMs) are introduced for their strong generalizability. This incurs a new problem: the knowledge encoded in the pre-trained VLMs may be disturbed when adapting to new tasks, compromising their inherent zero-shot ability. Existing methods tackle it by tuning VLMs with knowledge distillation on extra datasets, which demands heavy overhead. We propose the Distribution-aware Interference-free Knowledge Integration (DIKI) framework, retaining pre-trained knowledge of
  arXiv  Detail & Related papers  (2024-07-07T12:19:37Z)
• Unlearning with Control: Assessing Real-world Utility for Large Language Model Unlearning [97.2995389188179]
  Recent research has begun to approach large language models (LLMs) unlearning via gradient ascent (GA) Despite their simplicity and efficiency, we suggest that GA-based methods face the propensity towards excessive unlearning. We propose several controlling methods that can regulate the extent of excessive unlearning.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• A Closer Look at the Limitations of Instruction Tuning [52.587607091917214]
  We show that Instruction Tuning (IT) fails to enhance knowledge or skills in large language models (LLMs) We also show that popular methods to improve IT do not lead to performance improvements over a simple LoRA fine-tuned model. Our findings reveal that responses generated solely from pre-trained knowledge consistently outperform responses by models that learn any form of new knowledge from IT on open-source datasets.
  arXiv  Detail & Related papers  (2024-02-03T04:45:25Z)
• ReCoRe: Regularized Contrastive Representation Learning of World Model [21.29132219042405]
  We present a world model that learns invariant features using contrastive unsupervised learning and an intervention-invariant regularizer. Our method outperforms current state-of-the-art model-based and model-free RL methods and significantly improves on out-of-distribution point navigation tasks evaluated on the iGibson benchmark.
  arXiv  Detail & Related papers  (2023-12-14T15:53:07Z)
• Effective Decision Boundary Learning for Class Incremental Learning [17.716035569936384]
  Rehearsal approaches in class incremental learning (CIL) suffer from decision boundary overfitting to new classes. We present a simple but effective approach to tackle these two factors. Experiments show that the proposedL achieves the proposedL state-of-the-art performances on several CIL benchmarks.
  arXiv  Detail & Related papers  (2023-01-12T18:04:51Z)
• Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral Similarities [43.327357653393015]
  We propose a novel meta-learner-based framework for representation learning regarding behavioral similarities for reinforcement learning. We empirically demonstrate that our proposed framework outperforms state-of-the-art baselines on several benchmarks.
  arXiv  Detail & Related papers  (2022-12-26T11:11:23Z)
• Weighted Ensemble Self-Supervised Learning [67.24482854208783]
  Ensembling has proven to be a powerful technique for boosting model performance. We develop a framework that permits data-dependent weighted cross-entropy losses. Our method outperforms both in multiple evaluation metrics on ImageNet-1K.
  arXiv  Detail & Related papers  (2022-11-18T02:00:17Z)
• Discriminator-Guided Model-Based Offline Imitation Learning [11.856949845359853]
  offline imitation learning (IL) is a powerful method to solve decision-making problems from expert demonstrations without reward labels. We propose the Discriminator-guided Model-based offline Learning (DMIL) framework, which introduces a discriminator to simultaneously distinguish the dynamics correctness and suboptimality of model rollout data. Experimental results show that DMIL and its extension achieve superior performance and robustness compared to state-of-the-art offline IL methods under small datasets.
  arXiv  Detail & Related papers  (2022-07-01T07:28:18Z)
• Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters [76.36104006511684]
  Weakly-supervised object detection (WSOD) has emerged as an inspiring recent topic to avoid expensive instance-level object annotations. We defend the problem setting for improving localization performance by leveraging the bounding box regression knowledge from a well-annotated auxiliary dataset. Our method performs favorably against state-of-the-art WSOD methods and knowledge transfer model with similar problem setting.
  arXiv  Detail & Related papers  (2021-08-03T13:38:20Z)
• Regularized Behavior Value Estimation [31.332929202377]
  We introduce Regularized Behavior Value Estimation (R-BVE) R-BVE estimates the value of the behavior policy during training and only performs policy improvement at deployment time. We provide ample empirical evidence of R-BVE's effectiveness, including state-of-the-art performance on the RL Unplugged ATARI dataset.
  arXiv  Detail & Related papers  (2021-03-17T11:34:54Z)
• A new interpretable unsupervised anomaly detection method based on residual explanation [47.187609203210705]
  We present RXP, a new interpretability method to deal with the limitations for AE-based AD in large-scale systems. It stands out for its implementation simplicity, low computational cost and deterministic behavior. In an experiment using data from a real heavy-haul railway line, the proposed method achieved superior performance compared to SHAP.
  arXiv  Detail & Related papers  (2021-03-14T15:35:45Z)
• Efficient Estimation of Influence of a Training Instance [56.29080605123304]
  We propose an efficient method for estimating the influence of a training instance on a neural network model. Our method is inspired by dropout, which zero-masks a sub-network and prevents the sub-network from learning each training instance. We demonstrate that the proposed method can capture training influences, enhance the interpretability of error predictions, and cleanse the training dataset for improving generalization.
  arXiv  Detail & Related papers  (2020-12-08T04:31:38Z)
• MixKD: Towards Efficient Distillation of Large-scale Language Models [129.73786264834894]
  We propose MixKD, a data-agnostic distillation framework, to endow the resulting model with stronger generalization ability. We prove from a theoretical perspective that under reasonable conditions MixKD gives rise to a smaller gap between the error and the empirical error. Experiments under a limited-data setting and ablation studies further demonstrate the advantages of the proposed approach.
  arXiv  Detail & Related papers  (2020-11-01T18:47:51Z)

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.