Symbolic Explanation of Affinity-Based Reinforcement Learning Agents with Markov Models

08/26/2022
by   Charl Maree, et al.
0

The proliferation of artificial intelligence is increasingly dependent on model understanding. Understanding demands both an interpretation - a human reasoning about a model's behavior - and an explanation - a symbolic representation of the functioning of the model. Notwithstanding the imperative of transparency for safety, trust, and acceptance, the opacity of state-of-the-art reinforcement learning algorithms conceals the rudiments of their learned strategies. We have developed a policy regularization method that asserts the global intrinsic affinities of learned strategies. These affinities provide a means of reasoning about a policy's behavior, thus making it inherently interpretable. We have demonstrated our method in personalized prosperity management where individuals' spending behavior in time dictate their investment strategies, i.e. distinct spending personalities may have dissimilar associations with different investment classes. We now explain our model by reproducing the underlying prototypical policies with discretized Markov models. These global surrogates are symbolic representations of the prototypical policies.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/20/2022

Reinforcement Learning with Intrinsic Affinity for Personalized Asset Management

The common purpose of applying reinforcement learning (RL) to asset mana...
research
10/17/2022

A Symbolic Representation of Human Posture for Interpretable Learning and Reasoning

Robots that interact with humans in a physical space or application need...
research
01/21/2022

Reinforcement Learning Your Way: Agent Characterization through Policy Regularization

The increased complexity of state-of-the-art reinforcement learning (RL)...
research
09/12/2023

Goal Space Abstraction in Hierarchical Reinforcement Learning via Reachability Analysis

Open-ended learning benefits immensely from the use of symbolic methods ...
research
12/12/2017

Interpretable Policies for Reinforcement Learning by Genetic Programming

The search for interpretable reinforcement learning policies is of high ...
research
10/20/2018

Autonomous Self-Explanation of Behavior for Interactive Reinforcement Learning Agents

In cooperation, the workers must know how co-workers behave. However, an...
research
06/16/2021

Contrastive Reinforcement Learning of Symbolic Reasoning Domains

Abstract symbolic reasoning, as required in domains such as mathematics ...

Please sign up or login with your details

Forgot password? Click here to reset