S2Act: シンプルなスパイキングアクター
S2Act: Simple Spiking Actor
スパイキングニューラルネットワークを用いた強化学習ポリシーを、レートベースのLIFニューロンで近似し、ReLU活性化関数に整合するようにパラメータを調整することで、複雑な確率的環境でも安定して学習・展開できる軽量なフレームワークを提案した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Ugur Akcal, Seung Hyun Kim, Mikihisa Yuasa, Hamid Osooli, Jiarui Sun, Ribhav Sahu, Mattia Gazzola, Huy T. Tran, Girish Chowdhary
分類: cs.MA, cs.ET, cs.LG, cs.RO
原文アブストラクト
Spiking neural networks (SNNs) and biologically-inspired learning mechanisms are attractive in mobile robotics, where the size and performance of onboard neural network policies are constrained by power and computational budgets. Existing SNN approaches, such as population coding, reward modulation, and hybrid artificial neural network (ANN)-SNN architectures, have shown promising results; however, they face challenges in complex, highly stochastic environments due to SNN sensitivity to hyperparameters and inconsistent gradient signals. To address these challenges, we propose simple spiking actor (S2Act), a computationally lightweight framework that deploys an RL policy using an SNN in three steps: (1) architect an actor-critic model based on an approximated network of rate-based spiking neurons, (2) train the network with gradients using compatible activation functions, and (3) transfer the trained weights into physical parameters of rate-based leaky integrate-and-fire (LIF) neurons for inference and deployment. By globally shaping LIF neuron parameters such that their rate-based responses approximate ReLU activations, S2Act effectively mitigates the vanishing gradient problem, while pre-constraining LIF response curves reduces reliance on complex SNN-specific hyperparameter tuning. We demonstrate our method in two multi-agent stochastic environments (capture-the-flag and parking) that capture the complexity of multi-robot interactions, and deploy our trained policies on physical TurtleBot platforms using Intel's Loihi neuromorphic hardware. Our experimental results show that S2Act outperforms relevant baselines in task performance and real-time inference in nearly all considered scenarios, highlighting its potential for rapid prototyping and efficient real-world deployment of SNN-based RL policies.
