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

arXiv: https://arxiv.org/abs/2408.13018 · HTML: https://mlsanity.com/paper/2408.13018/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Spiking and neuromorphic RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 24 of its 55 references that are in the map.
- First posted on arXiv 23 Aug 2024.

## Placed in

- Deep reinforcement learning methods / [Spiking and neuromorphic RL](https://mlsanity.com/deeprl/spiking-and-neuromorphic-rl/)

## Builds on (most cited first, 24 of 24)

- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [A Brief Survey of Deep Reinforcement Learning](https://mlsanity.com/paper/1708.05866/) (2017)
- [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://mlsanity.com/paper/1609.07061/) (2016)
- [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016)
- [Deep Learning in Spiking Neural Networks](https://mlsanity.com/paper/1804.08150/) (2018)
- [Direct Training for Spiking Neural Networks: Faster, Larger, Better](https://mlsanity.com/paper/1809.05793/) (2018)
- [Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection](https://mlsanity.com/paper/1903.06530/) (2019)
- [Applications of Deep Reinforcement Learning in Communications and Networking: A Survey](https://mlsanity.com/paper/1810.07862/) (2018)
- [Scalable Methods for 8-bit Training of Neural Networks](https://mlsanity.com/paper/1805.11046/) (2018)
- [Taming the Noise in Reinforcement Learning via Soft Updates](https://mlsanity.com/paper/1512.08562/) (2015)
- [A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration](https://mlsanity.com/paper/2106.06984/) (2021)
- [Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey](https://mlsanity.com/paper/2005.00935/) (2020)
- [Exploring the Connection Between Binary and Spiking Neural Networks](https://mlsanity.com/paper/2002.10064/) (2020)
- [Event-driven Vision and Control for UAVs on a Neuromorphic Chip](https://mlsanity.com/paper/2108.03694/) (2021)
- [BS4NN: Binarized Spiking Neural Networks with Temporal Coding and Learning](https://mlsanity.com/paper/2007.04039/) (2020)
- [Strategy and Benchmark for Converting Deep Q-Networks to Event-Driven Spiking Neural Networks](https://mlsanity.com/paper/2009.14456/) (2020)
- [Minimum Energy Quantized Neural Networks](https://mlsanity.com/paper/1711.00215/) (2017)
- [Neuromorphic control for optic-flow-based landings of MAVs using the Loihi processor](https://mlsanity.com/paper/2011.00534/) (2020)
- [Towards Efficient Verification of Quantized Neural Networks](https://mlsanity.com/paper/2312.12679/) (2023)
- [Evolved Neuromorphic Control for High Speed Divergence-based Landings of MAVs](https://mlsanity.com/paper/2003.03118/) (2020)
- [RANC: Reconfigurable Architecture for Neuromorphic Computing](https://mlsanity.com/paper/2011.00624/) (2020)
- [NeuroPod: a real-time neuromorphic spiking CPG applied to robotics](https://mlsanity.com/paper/1904.11243/) (2019)
- [A Self-Driving Robot Using Deep Convolutional Neural Networks on Neuromorphic Hardware](https://mlsanity.com/paper/1611.01235/) (2016)
- [Binarized P-Network: Deep Reinforcement Learning of Robot Control from Raw Images on FPGA](https://mlsanity.com/paper/2109.04966/) (2021)

## Abstract (arXiv)

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.