41 accepted papers
Multi-agent deep Reinforcement Learning (RL) has made significant progress in developing intelligent game-playing agents in recent years. However, the efficient training of collective robots using multi-agent RL and the transfer of learned policies to real-world applications remain open research que…
Embodied AI research is undergoing a shift toward vision-centric perceptual paradigms. While massively parallel simulators have catalyzed breakthroughs in proprioception-based locomotion, their potential remains largely untapped for vision-centric tasks due to the prohibitive computational overhead …
To facilitate robot manipulation tasks, we propose ShapeAfford that reconstructs 3D object models with per-point affordance annotations from multi-view images and textual instructions. By integrating geometric modeling with affordance reasoning into an end-to-end framework, ShapeAfford leverages the
Autonomous navigation of unmanned ground vehicles (UGVs) in dynamic scenes is a challenging task that requires them to avoid obstacles and move toward the goal simultaneously. This paper proposes ALVO, an adaptive learning policy that leverages velocity obstacles for UGV navigation. ALVO employs an
We introduce AgentWorld, an interactive simulation platform for developing household mobile manipulation capabilities. Our platform combines automated scene construction that encompasses layout generation, semantic asset placement, visual material configuration, and physics simulation, with a dual-m…
Individual Large Language Models (LLMs) have demonstrated significant capabilities across various domains, such as healthcare and law. Recent studies also show that coordinated multi-agent systems exhibit enhanced decision-making and reasoning abilities through collaboration. However, due to the vul
Knowledge Graph Completion (KGC), which aims to infer missing or incomplete facts, is a crucial task for KGs. However, integrating the vital structural information of KGs into Large Language Models (LLMs) and outputting predictions deterministically remains challenging. To address this, we propose a…
The ability to simulate the effects of future actions on the world is a crucial ability of intelligent embodied agents, enabling agents to anticipate the effects of their actions and make plans accordingly. While a large body of existing work has explored how to construct such world models using vid…
Large Language Models (LLMs) have significantly impacted various domains, especially through organized LLM-driven autonomous agents. A representative scenario is in software development, where agents can collaborate in a team like humans, following predefined phases to complete sub-tasks sequentiall…
Large language models (LLMs) have achieved remarkable results across diverse downstream tasks, but their monolithic nature restricts scalability and efficiency in complex problem-solving. While recent research explores multi-agent collaboration among LLMs, most approaches rely on static organization…
Preference-based reinforcement learning (PbRL) bypasses complex reward engineering by learning from human feedback. However, due to the high cost of obtaining feedback, PbRL typically relies on a limited set of preference-labeled samples. This data scarcity introduces two key inefficiencies: (1) the…
Learning policy from offline datasets through offline reinforcement learning (RL) holds promise for scaling data-driven decision-making while avoiding unsafe and costly online interactions. However, real-world data collected from sensors or humans often contains noise and errors, posing a significan…
Circular accessible depth (CAD) provides a lightweight and robust traversability representation for autonomous navigation of unmanned ground vehicles (UGV). Aiming at the limitations of existing LiDAR-based methods in detecting low-thickness targets and executing semantic reasoning, we propose VCADN
Learning-based methods have improved locomotion skills of quadruped robots through deep reinforcement learning. However, the sim-to-real gap and low sample efficiency still limit the skill transfer. To address this issue, we propose an efficient model-based learning framework that combines a world m…
Physical Human-Scene Interaction (HSI) plays a crucial role in numerous applications. However, existing HSI techniques are limited to specific object dynamics and privileged information, which prevents the development of more comprehensive applications. To address this limitation, we introd…
Learning highly dynamic behaviors for robots has been a longstanding challenge. Traditional approaches have demonstrated robust locomotion, but the exhibited behaviors lack diversity and agility. They employ approximate models, which lead to compromises in performance. Data-driven approaches have be…
We propose HyperAgent, a reinforcement learning (RL) algorithm based on the hypermodel framework for exploration in RL. HyperAgent allows for the efficient incremental approximation of posteriors associated with an optimal action-value function ($Q^\star$) without the need for conjugacy and follows…
We consider the problem of policy transfer between two Markov Decision Processes (MDPs). We introduce a lemma based on existing theoretical results in reinforcement learning to measure the relativity gap between two arbitrary MDPs, that is the difference between any two cumulative expected returns d…
The robustness of legged locomotion is crucial for quadrupedal robots in challenging terrains. Recently, Reinforcement Learning (RL) has shown promising results in legged locomotion and various methods try to integrate privileged distillation, scene modeling, and external sensors to improve the gene…
We explore the potential of self-play training for large language models (LLMs) in a two-player adversarial language game called Adversarial Taboo. In this game, an attacker and a defender communicate around a target word only visible to the attacker. The attacker aims to induce the defender to spea…
Unsupervised reinforcement learning (URL) aims to learn general skills for unseen downstream tasks. Mutual Information Skill Learning (MISL) addresses URL by maximizing the mutual information between states and skills but lacks sufficient theoretical analysis, e.g., how well its learned skills can i…
Despite the impressive capabilities of Large Language Models (LLMs) on various tasks, they still struggle with scenarios that involves complex reasoning and planning. Self-correction and self-learning emerge as viable solutions, employing strategies that allow LLMs to refine their outputs and learn…
Offline reinforcement learning (RL) presents a promising approach for learning reinforced policies from offline datasets without the need for costly or unsafe interactions with the environment. However, datasets collected by humans in real-world environments are often noisy and may even be malicious…
Current model quantization methods have shown their promising capability in reducing storage space and computation complexity. However, due to the diversity of quantization forms supported by different hardware, one limitation of existing solutions is that usually require repeated optimization for d…
In this paper, we present a general learning framework for controlling a quadruped robot that can mimic the behavior of real animals and traverse challenging terrains. Our method consists of two steps: an imitation learning step to learn from motions of real animals, and a terrain adaptation step to…
Graph neural networks, which typically exchange information between local neighbors, often struggle to capture long-range interactions (LRIs) within the graph. Building a graph hierarchy via graph pooling methods is a promising approach to address this challenge; however, hierarchical information pr…
In this work, we study the simple yet universally applicable case of reward shaping in value-based Deep Reinforcement Learning (DRL). We show that reward shifting in the form of a linear transformation is equivalent to changing the initialization of the $Q$-function in function approximation. Based…
This research presents a novel Collective Robotic Construction (CRC) system named RECCraft. The RECCraft hardware system is composed of the mobile manipulation vehicles, the cubic blocks, and the folding ramp blocks. Solid connection and easy removal of the blocks are achieved by an electropermanent…
Offline reinforcement learning (RL) provides a promising direction to exploit massive amount of offline data for complex decision-making tasks. Due to the distribution shift issue, current offline RL algorithms are generally designed to be conservative in value estimation and action selection. Howev…
Solving goal-conditioned tasks with sparse rewards using self-supervised learning is promising because of its simplicity and stability over current reinforcement learning (RL) algorithms. A recent work, called Goal-Conditioned Supervised Learning (GCSL), provides a new learning framework by iterativ…
Exploration methods based on pseudo-count of transitions or curiosity of dynamics have achieved promising results in solving reinforcement learning with sparse rewards. However, such methods are usually sensitive to environmental dynamics-irrelevant information, e.g., white-noise. To handle such dyn…
One principled approach for provably efficient exploration is incorporating the upper confidence bound (UCB) into the value function as a bonus. However, UCB is specified to deal with linear and tabular settings and is incompatible with Deep Reinforcement Learning (DRL). In this paper, we propose a…
Neural network language model (NNLM) is an essential component of industrial ASR systems. One important challenge of training an NNLM is to leverage between scaling the learning process and handling big data. Conventional approaches such as block momentum provides a blockwise model update filtering…
3D instance segmentation, with a variety of applications in robotics and augmented reality, is in large demands these days. Unlike 2D images that are projective observations of the environment, 3D models provide metric reconstruction of the scenes without occlusion or scale ambiguity. In this paper,…
In off-policy deep reinforcement learning, it is usually hard to collect sufficient successful experiences with sparse rewards to learn from. Hindsight experience replay (HER) enables an agent to learn from failures by treating the achieved state of a failed experience as a pseudo goal. However, not…
We consider the problem of multi-agent reinforcement learning (MARL) in video game AI, where the agents are located in a spatial grid-world environment and the number of agents varies both within and across episodes. The challenge is to flexibly control an arbitrary number of agents while achieving…
A great challenge in cooperative decentralized multi-agent reinforcement learning (MARL) is generating diversified behaviors for each individual agent when receiving only a team reward. Prior studies have paid much effort on reward shaping or designing a centralized critic that can discriminatively…
This paper proposes a method for multi-class classification problems, where the number of classes K is large. The method, referred to as Candidates vs. Noises Estimation (CANE), selects a small subset of candidate classes and samples the remaining classes. We show that CANE is always consistent and…
We consider deep policy learning with only batched historical trajectories. The main challenge of this problem is that the learner no longer has a simulator or ``environment oracle'' as in most reinforcement learning settings. To solve this problem, we propose a monotonic advantage reweighted imitat…
Aiming at the practical usage of dense 3D reconstruction on portable devices, we propose FlashFusion, a Fast LArge-Scale High-resolution (sub-centimeter level) 3D reconstruction system without the use of GPU computing. It enables globally-consistent localization through a robust yet fast global bund…
In this paper a binary feature based Loop Closure Detection (LCD) method is proposed, which for the first time achieves higher precision-recall (PR) performance compared with state-of-the-art SIFT feature based approaches. The proposed system originates from our previous work Multi-Index hashing for…