Scalable Multi-task Learning Through Spiking Neural Networks With Adaptive Task-switching Policy For Intelligent Autonomous Agents

Abstract

Training resource-constrained autonomous agents on multiple tasks simultaneously is crucial for adapting to diverse real-world environments. Recent works employ reinforcement learning (RL) approach, but they still suffer from sub-optimal multi-task performance due to task interference. State-of-the-art works employ Spiking Neural Networks (SNNs) to improve RL-based multi-task learning and enable low-power/energy operations through network enhancements and spike-driven data stream processing. However, they rely on fixed task-switching intervals during its training, thus limiting its performance and scalability. To address this, we propose SwitchMT, a novel methodology that employs adaptive task-switching for effective, scalable, and simultaneous multi-task learning. SwitchMT employs the following key ideas: (1) leveraging a Deep Spiking Q-Network with active dendrites and dueling structure, that utilizes task-specific context signals to create specialized sub-networks; and (2) devising

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyputra2025scalable

Related papers

• Fully Spiking Actor Network With Intra-layer Connections For Reinforcement Learning (2024)0.00
• Deep Reinforcement Learning With Spiking Q-learning (2022)0.00
• Learning To Control Dynamical Agents Via Spiking Neural Networks And Metropolis-hastings Sampling (2025)0.00
• Learning First-to-spike Policies For Neuromorphic Control Using Policy Gradients (2018)8.60
• Energy-efficient Deep Reinforcement Learning With Spiking Transformers (2025)2.26
• Adaptive Surrogate Gradients For Sequential Reinforcement Learning In Spiking Neural Networks (2025)0.00
• A Novel Switch-type Policy Network For Resource Allocation Problems: Technical Report (2025)0.00
• A Low Latency Adaptive Coding Spiking Framework For Deep Reinforcement Learning (2022)7.16