Interpretable Policies For Reinforcement Learning By Genetic Programming

Abstract

The search for interpretable reinforcement learning policies is of high academic and industrial interest. Especially for industrial systems, domain experts are more likely to deploy autonomously learned controllers if they are understandable and convenient to evaluate. Basic algebraic equations are supposed to meet these requirements, as long as they are restricted to an adequate complexity. Here we introduce the genetic programming for reinforcement learning (GPRL) approach based on model-based batch reinforcement learning and genetic programming, which autonomously learns policy equations from pre-existing default state-action trajectory samples. GPRL is compared to a straight-forward method which utilizes genetic programming for symbolic regression, yielding policies imitating an existing well-performing, but non-interpretable policy. Experiments on three reinforcement learning benchmarks, i.e., mountain car, cart-pole balancing, and industrial benchmark, demonstrate the superiority

Stats

• citations92
• S2 citations—
• github stars0
• HF likes0
• heat score14.76
• arxiv keyhein2017interpretable

Related papers

• Evaluating Interpretable Reinforcement Learning By Distilling Policies Into Programs (2025)0.00
• Revisiting Generative Policies: A Simpler Reinforcement Learning Algorithmic Perspective (2024)0.00
• S-REINFORCE: A Neuro-symbolic Policy Gradient Approach For Interpretable Reinforcement Learning (2023)0.00
• Smoothing Policies And Safe Policy Gradients (2019)7.50
• "so, Tell Me About Your Policy...": Distillation Of Interpretable Policies From Deep Reinforcement Learning Agents (2025)0.00
• Programmatic Reinforcement Learning: Navigating Gridworlds (2024)0.00
• Generation Of Policy-level Explanations For Reinforcement Learning (2019)11.39
• Policy Optimization By Genetic Distillation (2017)0.00