Behavior alignment via reward function optimization
Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward
specific behaviors is a complex task. This is challenging since it requires the identification of …
specific behaviors is a complex task. This is challenging since it requires the identification of …
Comparing multi-armed bandit algorithms and Q-learning for multiagent action selection: a case study in route choice
TBF de Oliveira, ALC Bazzan… - … Joint Conference on …, 2018 - ieeexplore.ieee.org
The multi-armed bandit (MAB) problem is concerned with an agent choosing which arm of a
slot machine to play in order to optimize its reward. A family of reinforcement learning …
slot machine to play in order to optimize its reward. A family of reinforcement learning …
Reinforcement learning vs. rule-based adaptive traffic signal control: A Fourier basis linear function approximation for traffic signal control
Reinforcement learning is an efficient, widely used machine learning technique that
performs well when the state and action spaces have a reasonable size. This is rarely the …
performs well when the state and action spaces have a reasonable size. This is rarely the …
[PDF][PDF] A Reinforcement Learning Approach with Fourier Basis Linear Function Approximation for Traffic Signal Control.
Reinforcement learning is an efficient, widely used machine learning technique that
performs well when the state and action spaces are reasonable. This is rarely the case …
performs well when the state and action spaces are reasonable. This is rarely the case …
Competitive Evolution Multi-Agent Deep Reinforcement Learning
W Zhou, Y Chen, J Li - Proceedings of the 3rd International Conference …, 2019 - dl.acm.org
As an effective method to solve the optimal policy in multi-agent systems, multi-agent deep
reinforcement learning (MADRL) has achieved impressive results in many applications …
reinforcement learning (MADRL) has achieved impressive results in many applications …
On the Role of Reward Functions for Reinforcement Learning in the Traffic Assignment Problem
R Grunitzki, G de Oliveira Ramos - 2020 International Joint …, 2020 - ieeexplore.ieee.org
The traffic assignment problem (TAP) consists of assigning routes to road users in order to
minimize traffic congestion. Traditional methods for solving the TAP assume the existence of …
minimize traffic congestion. Traditional methods for solving the TAP assume the existence of …
[PDF][PDF] Stand by me: Learning to keep cohesion in the navigation of heterogeneous swarms
TM Grabe, FR Inácio, LS Marcolino, DG Macharet… - lancaster.ac.uk
A robotic swarm is a particular type of Multiagent System that employs a large number of
simpler agents in order to cooperatively perform different tasks. Oftentimes, the …
simpler agents in order to cooperatively perform different tasks. Oftentimes, the …