相关论文: Object-Aware Regularization for Addressing Causal …

State-of-the-art imitation learning from observation methods (ILfO) have recently made significant progress, but they still have some limitations: they need action-based supervised optimisation, assume that states have a single optimal…

The increased complexity of state-of-the-art reinforcement learning (RL) algorithms have resulted in an opacity that inhibits explainability and understanding. This has led to the development of several post-hoc explainability methods that…

Supervised imitation learning, also known as behavioral cloning, suffers from distribution drift leading to failures during policy execution. One approach to mitigate this issue is to allow an expert to correct the agent's actions during…

Consider learning an imitation policy on the basis of demonstrated behavior from multiple environments, with an eye towards deployment in an unseen environment. Since the observable features from each setting may be different, directly…

Current multi-modal models exhibit a notable misalignment with the human visual system when identifying objects that are visually assimilated into the background. Our observations reveal that these multi-modal models cannot distinguish…

Enabling autonomous robots to interact in unstructured environments with dynamic objects requires manipulation capabilities that can deal with clutter, changes, and objects' variability. This paper presents a comparison of different…

Learning With Opponent-Learning Awareness (LOLA) (Foerster et al. [2018a]) is a multi-agent reinforcement learning algorithm that typically learns reciprocity-based cooperation in partially competitive environments. However, LOLA often…

Robotic manipulation in complex open-world scenarios requires both reliable physical manipulation skills and effective and generalizable perception. In this paper, we propose a method where general purpose pretrained visual models serve as…

Behavior cloning has shown success in many sequential decision-making tasks by learning from expert demonstrations, yet they can be very sample inefficient and fail to generalize to unseen scenarios. One approach to these problems is to…

Iterative refinement -- start with a random guess, then iteratively improve the guess -- is a useful paradigm for representation learning because it offers a way to break symmetries among equally plausible explanations for the data. This…

AutoFocus-IL is a simple yet effective method to improve data efficiency and generalization in visual imitation learning by guiding policies to attend to task-relevant features rather than distractors and spurious correlations. Although…

Object detection limits its recognizable categories during the training phase, in which it can not cover all objects of interest for users. To satisfy the practical necessity, the incremental learning ability of the detector becomes a…

Behavior cloning is a common imitation learning paradigm. Under behavior cloning the robot collects expert demonstrations, and then trains a policy to match the actions taken by the expert. This works well when the robot learner visits…

Accurate and unambiguous guidelines are critical for large language model (LLM) based graders, yet manually crafting these prompts is often sub-optimal as LLMs can misinterpret expert guidelines or lack necessary domain specificity.…

Multi-objective reinforcement learning (MORL) is the generalization of standard reinforcement learning (RL) approaches to solve sequential decision making problems that consist of several, possibly conflicting, objectives. Generally, in…

As a key component to intuitive cognition and reasoning solutions in human intelligence, causal knowledge provides great potential for reinforcement learning (RL) agents' interpretability towards decision-making by helping reduce the…

We introduce Correspondence-Oriented Imitation Learning (COIL), a conditional policy learning framework for visuomotor control with a flexible task representation in 3D. At the core of our approach, each task is defined by the intended…

In this paper, we propose the use of generative artificial intelligence (AI) to improve zero-shot performance of a pre-trained policy by altering observations during inference. Modern robotic systems, powered by advanced neural networks,…

Imitation learning is a widely used policy learning method that enables intelligent agents to acquire complex skills from expert demonstrations. The input to the imitation learning algorithm is usually composed of both the current…

To enhance the cross-target and cross-scene generalization of target-driven visual navigation based on deep reinforcement learning (RL), we introduce an information-theoretic regularization term into the RL objective. The regularization…