Graph Neural Networks and Reinforcement Learning for Behavior Generation in Semantic Environments

2020-06-22 · Patrick Hart, Alois Knoll

Most reinforcement learning approaches used in behavior generation utilize vectorial information as input. However, this requires the network to have a pre-defined input-size -- in semantic environments this means assuming the maximum number of vehicles. Additionally, this vectorial representation is not invariant to the order and number of vehicles. To mitigate the above-stated disadvantages, we propose combining graph neural networks with actor-critic reinforcement learning. As graph neural networks apply the same network to every vehicle and aggregate incoming edge information, they are invariant to the number and order of vehicles. This makes them ideal candidates to be used as networks in semantic environments -- environments consisting of objects lists. Graph neural networks exhibit some other advantages that make them favorable to be used in semantic environments. The relational information is explicitly given and does not have to be inferred. Moreover, graph neural networks propagate information through the network and can gather higher-degree information. We demonstrate our approach using a highway lane-change scenario and compare the performance of graph neural networks to conventional ones. We show that graph neural networks are capable of handling scenarios with a varying number and order of vehicles during training and application.

📄 PDF Abstract BibTeX arXiv:2006.12576

Code (2)

bark-simulator/bark-ml/tree/master/experiments 공식 구현 tf

bark-simulator/bark-ml tf

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Bridging Scene Understanding and Task Execution with Flexible Simulation Environments

2020-11-20 · Zachary Ravichandran, J. Daniel Griffith, Benjamin Smith, Costas Frost

Significant progress has been made in scene understanding which seeks to build 3D, metric and object-oriented representations of the world. Concurrently, reinforcement learning has made impressive strides largely enabled…

Graph Generation reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+3

Unifying Large Language Model and Deep Reinforcement Learning for Human-in-Loop Interactive Socially-aware Navigation

2024-03-22 · Weizheng Wang, Ike Obi, Aniket Bera, Byung-Cheol Min

Navigating human-filled spaces is crucial for the interactive social robots to support advanced services, such as cooperative carrying, which enables service provision in complex and crowded environments while adapting b…

Benchmarking Deep Reinforcement Learning Language Modeling Language Modelling+3

Graph Convolution-Based Deep Reinforcement Learning for Multi-Agent Decision-Making in Mixed Traffic Environments

2022-01-30 · Qi Liu, Zirui Li, Xueyuan Li, Jingda Wu 외

An efficient and reliable multi-agent decision-making system is highly demanded for the safe and efficient operation of connected autonomous vehicles in intelligent transportation systems. Current researches mainly focus…

Autonomous Vehicles Decision Making Deep Reinforcement Learning Graph Neural Network+2

Deep Surrogate Assisted Generation of Environments

2022-06-09 · Varun Bhatt, Bryon Tjanaka, Matthew C. Fontaine, Stefanos Nikolaidis

Recent progress in reinforcement learning (RL) has started producing generally capable agents that can solve a distribution of complex environments. These agents are typically tested on fixed, human-authored environments…

Diversity Reinforcement Learning (RL)

Multi-action Tangled Program Graphs for Multi-task Reinforcement Learning with Continuous Control

2026-04-28 · Quentin Vacher, Nicolas Beuve, Mickaël Dardaillon, Karol Desnos arxiv

Over the past few decades, machine learning has been widely used to learn complex tasks. Reinforcement Learning (RL), inspired by human behavior, is a great example, as it involves developing specific behaviours for spec…

Reinforcement Learning Continuous Control