Related papers: SS-MAIL: Self-Supervised Multi-Agent Imitation Lea…

Cooperative problems under continuous control have always been the focus of multi-agent reinforcement learning. Existing algorithms suffer from the problem of uneven learning degree with the increase of the number of agents. In this paper,…

Imitation learning is an effective tool for robotic learning tasks where specifying a reinforcement learning (RL) reward is not feasible or where the exploration problem is particularly difficult. Imitation, typically behavior cloning or…

Hierarchical Imitation Learning (HIL) has been proposed to recover highly-complex behaviors in long-horizon tasks from expert demonstrations by modeling the task hierarchy with the option framework. Existing methods either overlook the…

Imitation learning (IL) enables agents to mimic expert behaviors. Most previous IL techniques focus on precisely imitating one policy through mass demonstrations. However, in many applications, what humans require is the ability to perform…

Learning from demonstrations has made great progress over the past few years. However, it is generally data hungry and task specific. In other words, it requires a large amount of data to train a decent model on a particular task, and the…

This search introduces the Multimodal Socialized Learning Framework (M-S2L), designed to foster emergent social intelligence in AI agents by integrating Multimodal Large Language Models (M-LLMs) with social learning mechanisms. The…

Imitation learning trains a policy from expert demonstrations. Imitation learning approaches have been designed from various principles, such as behavioral cloning via supervised learning, apprenticeship learning via inverse reinforcement…

Critical sectors of human society are progressing toward the adoption of powerful artificial intelligence (AI) agents, which are trained individually on behalf of self-interested principals but deployed in a shared environment. Short of…

While Large Language Models (LLMs) hold promise to become autonomous agents, they often explore suboptimally in sequential decision-making. Recent work has sought to enhance this capability via supervised fine-tuning (SFT) or reinforcement…

Multimodal recommendation has attracted extensive attention by leveraging heterogeneous modality information to alleviate data sparsity and improve recommendation accuracy. Existing methods have attempted to replace ID embeddings with…

We study the problem of offline Imitation Learning (IL) where an agent aims to learn an optimal expert behavior policy without additional online environment interactions. Instead, the agent is provided with a supplementary offline dataset…

Autonomous driving has attracted great attention from both academics and industries. To realise autonomous driving, Deep Imitation Learning (DIL) is treated as one of the most promising solutions, because it improves autonomous driving…

Embodied agents, such as robots and virtual characters, must continuously select actions to execute tasks effectively, solving complex sequential decision-making problems. Given the difficulty of designing such controllers manually,…

Self-driving cars and autonomous driving research has been receiving considerable attention as major promising prospects in modern artificial intelligence applications. According to the evolution of advanced driver assistance system (ADAS),…

Combining the respective advantages of cross-modality images can compensate for the lack of information in the single modality, which has attracted increasing attention of researchers into multi-modal image matching tasks. Meanwhile, due to…

In multi-agent systems (MAS), the dynamic interaction among multiple decision-makers is driven by their innate values, affecting the environment's state, and can cause specific behavioral patterns to emerge. On the other hand, innate values…

Imitation learning (IL) is a framework that learns to imitate expert behavior from demonstrations. Recently, IL shows promising results on high dimensional and control tasks. However, IL typically suffers from sample inefficiency in terms…

Class-incremental learning (CIL) under an exemplar-free constraint has presented a significant challenge. Existing methods adhering to this constraint are prone to catastrophic forgetting, far more so than replay-based techniques that…

Generative Adversarial Imitation Learning (GAIL) can learn policies without explicitly defining the reward function from demonstrations. GAIL has the potential to learn policies with high-dimensional observations as input, e.g., images. By…

In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine…