MoËT: Interpretable and Verifiable Reinforcement Learning via Mixture of Expert Trees

06/16/2019
by   Marko Vasic, et al.
0

Deep Reinforcement Learning (DRL) has led to many recent breakthroughs on complex control tasks, such as defeating the best human player in the game of Go. However, decisions made by the DRL agent are not explainable, hindering its applicability in safety-critical settings. Viper, a recently proposed technique, constructs a decision tree policy by mimicking the DRL agent. Decision trees are interpretable as each action made can be traced back to the decision rule path that lead to it. However, one global decision tree approximating the DRL policy has significant limitations with respect to the geometry of decision boundaries. We propose MoËT, a more expressive, yet still interpretable model based on Mixture of Experts, consisting of a gating function that partitions the state space, and multiple decision tree experts that specialize on different partitions. We propose a training procedure to support non-differentiable decision tree experts and integrate it into imitation learning procedure of Viper. We evaluate our algorithm on four OpenAI gym environments, and show that the policy constructed in such a way is more performant and better mimics the DRL agent by lowering mispredictions and increasing the reward. We also show that MoËT policies are amenable for verification using off-the-shelf automated theorem provers such as Z3.

READ FULL TEXT
research
05/22/2018

Verifiable Reinforcement Learning via Policy Extraction

While deep reinforcement learning has successfully solved many challengi...
research
11/15/2020

CDT: Cascading Decision Trees for Explainable Reinforcement Learning

Deep Reinforcement Learning (DRL) has recently achieved significant adva...
research
09/20/2020

Interpretable-AI Policies using Evolutionary Nonlinear Decision Trees for Discrete Action Systems

Black-box artificial intelligence (AI) induction methods such as deep re...
research
03/28/2020

Learning medical triage from clinicians using Deep Q-Learning

Medical Triage is of paramount importance to healthcare systems, allowin...
research
09/06/2023

On Reducing Undesirable Behavior in Deep Reinforcement Learning Models

Deep reinforcement learning (DRL) has proven extremely useful in a large...
research
08/31/2021

Learning to Synthesize Programs as Interpretable and Generalizable Policies

Recently, deep reinforcement learning (DRL) methods have achieved impres...
research
02/25/2021

Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methods

Current work in explainable reinforcement learning generally produces po...

Please sign up or login with your details

Forgot password? Click here to reset