Reinforcement Learning With Low-complexity Liquid State Machines

Abstract

We propose reinforcement learning on simple networks consisting of random connections of spiking neurons (both recurrent and feed-forward) that can learn complex tasks with very little trainable parameters. Such sparse and randomly interconnected recurrent spiking networks exhibit highly non-linear dynamics that transform the inputs into rich high-dimensional representations based on past context. The random input representations can be efficiently interpreted by an output (or readout) layer with trainable parameters. Systematic initialization of the random connections and training of the readout layer using Q-learning algorithm enable such small random spiking networks to learn optimally and achieve the same learning efficiency as humans on complex reinforcement learning tasks like Atari games. The spike-based approach using small random recurrent networks provides a computationally efficient alternative to state-of-the-art deep reinforcement learning networks with several layers of t

Stats

• citations17
• S2 citations—
• github stars0
• HF likes0
• heat score9.41
• arxiv keyponghiran2019reinforcement

Related papers

• Deep Reinforcement Learning With Spiking Q-learning (2022)0.00
• Learning Fast Changing Slow In Spiking Neural Networks (2024)3.58
• Reinforcement Learning With A Network Of Spiking Agents (2019)0.00
• Human-level Control Through Directly-trained Deep Spiking Q-networks (2021)12.40
• Fully Spiking Actor Network With Intra-layer Connections For Reinforcement Learning (2024)0.00
• Reservoir Computing For Fast, Simplified Reinforcement Learning On Memory Tasks (2024)0.00
• Eau De \(q\)-network: Adaptive Distillation Of Neural Networks In Deep Reinforcement Learning (2025)0.00
• Dynamic Sparse Training For Deep Reinforcement Learning (2021)0.00