Fast Reinforcement Learning With Incremental Gaussian Mixture Models

Abstract

This work presents a novel algorithm that integrates a data-efficient function approximator with reinforcement learning in continuous state spaces. An online and incremental algorithm capable of learning from a single pass through data, called Incremental Gaussian Mixture Network (IGMN), was employed as a sample-efficient function approximator for the joint state and Q-values space, all in a single model, resulting in a concise and data-efficient algorithm, i.e., a reinforcement learning algorithm that learns from very few interactions with the environment. Results are analyzed to explain the properties of the obtained algorithm, and it is observed that the use of the IGMN function approximator brings some important advantages to reinforcement learning in relation to conventional neural networks trained by gradient descent methods.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypinto2020fast

Related papers

• Online Reinforcement Learning Via Sparse Gaussian Mixture Model Q-functions (2025)0.00
• Task-agnostic Online Reinforcement Learning With An Infinite Mixture Of Gaussian Processes (2020)0.00
• Mixed Policy Gradient: Off-policy Reinforcement Learning Driven Jointly By Data And Model (2021)0.00
• Probabilistic Mixture-of-experts For Efficient Deep Reinforcement Learning (2021)0.00
• Adaptive Discretization For Episodic Reinforcement Learning In Metric Spaces (2019)2.26
• Distributionally Robust Model-based Reinforcement Learning With Large State Spaces (2023)0.00
• GB-DQN: Gradient Boosted DQN Models For Non-stationary Reinforcement Learning (2025)0.00
• Smoothed Action Value Functions For Learning Gaussian Policies (2018)0.00