FPGA Implementation of Q-RTS for Real-Time Swarm Intelligence Systems
Authors:
- 1 November 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 116-120
Abstract
We propose an architectural blueprint to implement Q-RTS, Q-Learning Real-Time Swarm Reinforcement Learning algorithm, on FPGA. The design solution is built on FPGA-based Centralized RL Processing Units (CRLPU). A CRLPU processes local and global state-action matrices and exchanges information frames with low-power Microcontroller-based Agents. The novel architecture implementation, for up to 32 Agents with up to 512 states, on a Xilinx Ultrascale device shows low resource requirements in terms of CLB (7%) and memory (2% FF and 22% BRAM). Performance metrics show that the required energy per generated action is always lower than 1 µJ.Keywords
This publication has 8 references indexed in Scilit:
- An Efficient Hardware Implementation of Reinforcement Learning: The Q-Learning AlgorithmIEEE Access, 2019
- Small Lung Nodules Detection Based on Fuzzy-Logic and Probabilistic Neural Network With Bioinspired Reinforcement LearningIEEE Transactions on Fuzzy Systems, 2019
- Design and Requirements for a Mobile Robot for Team CooperationMechanisms and Machine Science, 2019
- A Reinforcement Learning-Based QAM/PSK Symbol SynchronizerIEEE Access, 2019
- Q‐RTS: a real‐time swarm intelligence based on multi‐agent Q‐learningElectronics Letters, 2019
- Reinforcement learning versus evolutionary computation: A survey on hybrid algorithmsSwarm and Evolutionary Computation, 2019
- Parallel Implementation of Reinforcement Learning Q-Learning Technique for FPGAIEEE Access, 2018
- Q-learningMachine Learning, 1992