Trapezoidal Gradient Descent For Effective Reinforcement Learning In Spiking Networks

Abstract

With the rapid development of artificial intelligence technology, the field of reinforcement learning has continuously achieved breakthroughs in both theory and practice. However, traditional reinforcement learning algorithms often entail high energy consumption during interactions with the environment. Spiking Neural Network (SNN), with their low energy consumption characteristics and performance comparable to deep neural networks, have garnered widespread attention. To reduce the energy consumption of practical applications of reinforcement learning, researchers have successively proposed the Pop-SAN and MDC-SAN algorithms. Nonetheless, these algorithms use rectangular functions to approximate the spike network during the training process, resulting in low sensitivity, thus indicating room for improvement in the training effectiveness of SNN. Based on this, we propose a trapezoidal approximation gradient method to replace the spike network, which not only preserves the original stabl

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypan2024trapezoidal

Related papers

• Adaptive Surrogate Gradients For Sequential Reinforcement Learning In Spiking Neural Networks (2025)0.00
• Deep Reinforcement Learning With Population-coded Spiking Neural Network For Continuous Control (2020)0.00
• Deep Reinforcement Learning With Spiking Q-learning (2022)0.00
• Learning First-to-spike Policies For Neuromorphic Control Using Policy Gradients (2018)8.60
• Fully Spiking Actor Network With Intra-layer Connections For Reinforcement Learning (2024)0.00
• Energy-efficient Deep Reinforcement Learning With Spiking Transformers (2025)2.26
• Population-coding And Dynamic-neurons Improved Spiking Actor Network For Reinforcement Learning (2021)0.00
• GRSN: Gated Recurrent Spiking Neurons For Pomdps And MARL (2024)2.26