Related papers: Multi-expert learning of adaptive legged locomotio…

We propose a deep reinforcement learning (DRL) methodology for the tracking, obstacle avoidance, and formation control of nonholonomic robots. By separating vision-based control into a perception module and a controller module, we can train…

Quadrupedal robots have demonstrated exceptional locomotion capabilities through Reinforcement Learning (RL), including extreme parkour maneuvers. However, integrating locomotion skills with navigation in quadrupedal robots has not been…

Mixture-of-Experts (MoE) architectures have become the dominant choice for scaling Large Language Models (LLMs), activating only a subset of parameters per token. While MoE architectures are primarily adopted for computational efficiency,…

This paper proposes an end-to-end deep reinforcement learning approach for mobile robot navigation with dynamic obstacles avoidance. Using experience collected in a simulation environment, a convolutional neural network (CNN) is trained to…

Meta-Reinforcement Learning (Meta-RL) aims to acquire meta-knowledge for quick adaptation to diverse tasks. However, applying these policies in real-world environments presents a significant challenge in balancing rapid adaptability with…

Autonomous navigation capabilities play a critical role in service robots operating in environments where human interactions are pivotal, due to the dynamic and unpredictable nature of these environments. However, the variability in human…

This paper focuses on spectrum sharing in heterogeneous wireless networks, where nodes with different Media Access Control (MAC) protocols to transmit data packets to a common access point over a shared wireless channel. While previous…

Recent Vision-Language-Action (VLA) models reformulate vision-language models by tuning them with millions of robotic demonstrations. While they perform well when fine-tuned for a single embodiment or task family, extending them to…

Traditional RL-based locomotion controllers often suffer from low data efficiency, requiring extensive interaction to achieve robust performance. We present a model-based reinforcement learning (MBRL) framework that improves sample…

Equipping quadruped robots with manipulators provides unique loco-manipulation capabilities, enabling diverse practical applications. This integration creates a more complex system that has increased difficulties in modeling and control.…

As the capabilities of large language models (LLMs) continue to expand, aligning these models with human values remains a significant challenge. Recent studies show that reasoning abilities contribute significantly to model safety, while…

This paper proposes the transition-net, a robust transition strategy that expands the versatility of robot locomotion in the real-world setting. To this end, we start by distributing the complexity of different gaits into dedicated…

We show that a Modular Neural Network (MNN) can combine various speech enhancement modules, each of which is a Deep Neural Network (DNN) specialized on a particular enhancement job. Differently from an ordinary ensemble technique that…

Parameter-efficient fine-tuning techniques like Low-Rank Adaptation (LoRA) have revolutionized the adaptation of large language models (LLMs) to diverse tasks. Recent efforts have explored mixtures of LoRA modules for multi-task settings.…

Animals have remarkable abilities to adapt locomotion to different terrains and tasks. However, robots trained by means of reinforcement learning are typically able to solve only a single task and a transferred policy is usually inferior to…

Large language models (LLMs) have demonstrated impressive capabilities in aiding developers with tasks like code comprehension, generation, and translation. Supporting multilingual programming -- i.e., coding tasks across multiple…

Multimodal large language models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, a generalist MLLM typically underperforms compared with a specialist MLLM on most VL tasks, which can be…

Meta-learning often referred to as learning-to-learn is a promising notion raised to mimic human learning by exploiting the knowledge of prior tasks but being able to adapt quickly to novel tasks. A plethora of models has emerged in this…

Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations. Prior approaches for demonstration-guided RL treat every new…

Transformer-based Mixture-of-Experts (MoE) models have been driving several recent technological advancements in Natural Language Processing (NLP). These MoE models adopt a router mechanism to determine which experts to activate for routing…