Explainable Deep Reinforcement Learning Using Introspection In A Non-episodic Task

Abstract

Explainable reinforcement learning allows artificial agents to explain their behavior in a human-like manner aiming at non-expert end-users. An efficient alternative of creating explanations is to use an introspection-based method that transforms Q-values into probabilities of success used as the base to explain the agent's decision-making process. This approach has been effectively used in episodic and discrete scenarios, however, to compute the probability of success in non-episodic and more complex environments has not been addressed yet. In this work, we adapt the introspection method to be used in a non-episodic task and try it in a continuous Atari game scenario solved with the Rainbow algorithm. Our initial results show that the probability of success can be computed directly from the Q-values for all possible actions.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyayala2021explainable

Related papers

• Explaining Deep Reinforcement Learning Agents In The Atari Domain Through A Surrogate Model (2021)0.00
• Generating Explanations From Deep Reinforcement Learning Using Episodic Memory (2022)0.00
• Experiential Explanations For Reinforcement Learning (2022)2.26
• Learn To Interpret Atari Agents (2018)0.00
• What Did You Think Would Happen? Explaining Agent Behaviour Through Intended Outcomes (2020)0.00
• Counterfactual State Explanations For Reinforcement Learning Agents Via Generative Deep Learning (2021)13.23
• Explainability In Deep Reinforcement Learning (2020)0.00
• Causal State Distillation For Explainable Reinforcement Learning (2023)0.00