Related papers: MisoDICE: Multi-Agent Imitation from Unlabeled Mix…

Adversarial methods for imitation learning have been shown to perform well on various control tasks. However, they require a large number of environment interactions for convergence. In this paper, we propose an end-to-end differentiable…

Class-incremental with repetition (CIR), where previously trained classes repeatedly introduced in future tasks, is a more realistic scenario than the traditional class incremental setup, which assumes that each task contains unseen…

The goal of imitation learning is to mimic expert behavior from demonstrations, without access to an explicit reward signal. A popular class of approach infers the (unknown) reward function via inverse reinforcement learning (IRL) followed…

Large Language Models (LLMs) demonstrate strong performance but often lack interpretable reasoning. This paper introduces the Multi-Agent Collaboration Framework for Diverse Thinking Modes (DiMo), which enhances both performance and…

In multi-agent systems, complex interacting behaviors arise due to the high correlations among agents. However, previous work on modeling multi-agent interactions from demonstrations is primarily constrained by assuming the independence…

Most existing distance metric learning approaches use fully labeled data to learn the sample similarities in an embedding space. We present a self-training framework, SLADE, to improve retrieval performance by leveraging additional…

Offline Imitation Learning (IL) with imperfect demonstrations has garnered increasing attention owing to the scarcity of expert data in many real-world domains. A fundamental problem in this scenario is how to extract positive behaviors…

Communication is essential in coordinating the behaviors of multiple agents. However, existing methods primarily emphasize content, timing, and partners for information sharing, often neglecting the critical aspect of integrating shared…

Addressing multiagent decision problems in AI, especially those involving collaborative or competitive agents acting concurrently in a partially observable and stochastic environment, remains a formidable challenge. While Interactive…

Multi-label image classification is a fundamental but challenging task towards general visual understanding. Existing methods found the region-level cues (e.g., features from RoIs) can facilitate multi-label classification. Nevertheless,…

Imitation can be viewed as a means of enhancing learning in multiagent environments. It augments an agent's ability to learn useful behaviors by making intelligent use of the knowledge implicit in behaviors demonstrated by cooperative…

Imitation Learning (IL) can generate computationally efficient policies from demonstrations provided by Model Predictive Control (MPC). However, IL methods often require extensive data-collection and training efforts, limiting changes to…

Robust imitation learning using disturbance injections overcomes issues of limited variation in demonstrations. However, these methods assume demonstrations are optimal, and that policy stabilization can be learned via simple augmentations.…

We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised,…

Existing imitation learning works mainly assume that the demonstrator who collects demonstrations shares the same dynamics as the imitator. However, the assumption limits the usage of imitation learning, especially when collecting…

Imitation learning (IL) enables autonomous behavior by learning from expert demonstrations. While more sample-efficient than comparative alternatives like reinforcement learning, IL is sensitive to compounding errors induced by distribution…

Decentralized learning with private data is a central problem in machine learning. We propose a novel distillation-based decentralized learning technique that allows multiple agents with private non-iid data to learn from each other,…

Co-designing autonomous robotic agents involves simultaneously optimizing the controller and physical design of the agent. Its inherent bi-level optimization formulation necessitates an outer loop design optimization driven by an inner loop…

We propose using active learning based techniques to further improve the state-of-the-art semi-supervised learning MixMatch algorithm. We provide a thorough empirical evaluation of several active-learning and baseline methods, which…

We propose UnMixMatch, a semi-supervised learning framework which can learn effective representations from unconstrained unlabelled data in order to scale up performance. Most existing semi-supervised methods rely on the assumption that…