Robust Iterative Value Conversion: Deep Reinforcement Learning for Neurochip-driven Edge Robots

TL;DR

This paper introduces Robust Iterative Value Conversion (RIVC), a deep reinforcement learning method that improves policy robustness and efficiency for neurochip-driven edge robots by reducing conversion errors between neural network representations.

Contribution

The paper proposes RIVC, a novel DRL approach that minimizes conversion errors and enhances policy robustness for neurochip implementation, enabling low-power, high-speed edge robot control.

Findings

RIVC reduces power consumption to 1/15 of edge CPU.

RIVC increases calculation speed fivefold compared to CPU.

Previous methods failed to train policies without conversion error mitigation.

Abstract

A neurochip is a device that reproduces the signal processing mechanisms of brain neurons and calculates Spiking Neural Networks (SNNs) with low power consumption and at high speed. Thus, neurochips are attracting attention from edge robot applications, which suffer from limited battery capacity. This paper aims to achieve deep reinforcement learning (DRL) that acquires SNN policies suitable for neurochip implementation. Since DRL requires a complex function approximation, we focus on conversion techniques from Floating Point NN (FPNN) because it is one of the most feasible SNN techniques. However, DRL requires conversions to SNNs for every policy update to collect the learning samples for a DRL-learning cycle, which updates the FPNN policy and collects the SNN policy samples. Accumulative conversion errors can significantly degrade the performance of the SNN policies. We propose Robust Iterative Value Conversion (RIVC) as a DRL that incorporates conversion error reduction and robustness to conversion errors. To reduce them, FPNN is optimized with the same number of quantization bits as an SNN. The FPNN output is not significantly changed by quantization. To robustify the conversion error, an FPNN policy that is applied with quantization is updated to increase the gap between the probability of selecting the optimal action and other actions. This step prevents unexpected replacements of the policy's optimal actions. We verified RIVC's effectiveness on a neurochip-driven robot. The results showed that RIVC consumed 1/15 times less power and increased the calculation speed by five times more than an edge CPU (quad-core ARM Cortex-A72). The previous framework with no countermeasures against conversion errors failed to train the policies. Videos from our experiments are available: https://youtu.be/Q5Z0-BvK1Tc.