Feature-Based Interpretable Reinforcement Learning based on State-Transition Models
arXiv:2105.07099 · doi:10.1109/SMC52423.2021.9658917
Abstract
Growing concerns regarding the operational usage of AI models in the real-world has caused a surge of interest in explaining AI models' decisions to humans. Reinforcement Learning is not an exception in this regard. In this work, we propose a method for offering local explanations on risk in reinforcement learning. Our method only requires a log of previous interactions between the agent and the environment to create a state-transition model. It is designed to work on RL environments with either continuous or discrete state and action spaces. After creating the model, actions of any agent can be explained in terms of the features most influential in increasing or decreasing risk or any other desirable objective function in the locality of the agent. Through experiments, we demonstrate the effectiveness of the proposed method in providing such explanations.
References in corpus (7)
- Addressing Function Approximation Error in Actor-Critic Methods
- Verifiable Reinforcement Learning via Policy Extraction
- Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning Approach
- Particle Swarm Optimization for Generating Interpretable Fuzzy Reinforcement Learning Policies
- Dot-to-Dot: Explainable Hierarchical Reinforcement Learning for Robotic Manipulation
- Model-Based Reinforcement Learning for Sepsis Treatment
- Optimization Methods for Interpretable Differentiable Decision Trees in Reinforcement Learning