Collaborative Visual Navigation
arXiv:2107.01151
Abstract
As a fundamental problem for Artificial Intelligence, multi-agent system (MAS) is making rapid progress, mainly driven by multi-agent reinforcement learning (MARL) techniques. However, previous MARL methods largely focused on grid-world like or game environments; MAS in visually rich environments has remained less explored. To narrow this gap and emphasize the crucial role of perception in MAS, we propose a large-scale 3D dataset, CollaVN, for multi-agent visual navigation (MAVN). In CollaVN, multiple agents are entailed to cooperatively navigate across photo-realistic environments to reach target locations. Diverse MAVN variants are explored to make our problem more general. Moreover, a memory-augmented communication framework is proposed. Each agent is equipped with a private, external memory to persistently store communication information. This allows agents to make better use of their past communication information, enabling more efficient collaboration and robust long-term planning. In our experiments, several baselines and evaluation metrics are designed. We also empirically verify the efficacy of our proposed MARL approach across different MAVN task settings.
References in corpus (23)
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- Dota 2 with Large Scale Deep Reinforcement Learning
- Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
- A Survey and Critique of Multiagent Deep Reinforcement Learning
- On Evaluation of Embodied Navigation Agents
- Counterfactual Multi-Agent Policy Gradients
- Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problems
- AI2-THOR: An Interactive 3D Environment for Visual AI
- Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games
- Building Generalizable Agents with a Realistic and Rich 3D Environment
- Learning to Explore using Active Neural SLAM
- Emergence of Grounded Compositional Language in Multi-Agent Populations
- Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?
- Emergent Complexity via Multi-Agent Competition
- Multi-Agent Cooperation and the Emergence of (Natural) Language
- Neural SLAM: Learning to Explore with External Memory
- HoME: a Household Multimodal Environment
- Learning to Schedule Communication in Multi-agent Reinforcement Learning
- PyRobot: An Open-source Robotics Framework for Research and Benchmarking
- iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenes
- Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation