Reinforcement Learning in an Adaptable Chess Environment for Detecting Human-understandable Concepts

11/10/2022
by   Patrik Hammersborg, et al.
0

Self-trained autonomous agents developed using machine learning are showing great promise in a variety of control settings, perhaps most remarkably in applications involving autonomous vehicles. The main challenge associated with self-learned agents in the form of deep neural networks, is their black-box nature: it is impossible for humans to interpret deep neural networks. Therefore, humans cannot directly interpret the actions of deep neural network based agents, or foresee their robustness in different scenarios. In this work, we demonstrate a method for probing which concepts self-learning agents internalise in the course of their training. For demonstration, we use a chess playing agent in a fast and light environment developed specifically to be suitable for research groups without access to enormous computational resources or machine learning models.

READ FULL TEXT
research
02/27/2020

Training Adversarial Agents to Exploit Weaknesses in Deep Control Policies

Deep learning has become an increasingly common technique for various co...
research
04/11/2021

The Atari Data Scraper

Reinforcement learning has made great strides in recent years due to the...
research
10/22/2016

Reinforcement Learning in Conflicting Environments for Autonomous Vehicles

In this work, we investigate the application of Reinforcement Learning t...
research
10/14/2018

Distributed learning of deep neural network over multiple agents

In domains such as health care and finance, shortage of labeled data and...
research
09/08/2017

Towards Proving the Adversarial Robustness of Deep Neural Networks

Autonomous vehicles are highly complex systems, required to function rel...
research
04/21/2022

Accelerating Machine Learning via the Weber-Fechner Law

The Weber-Fechner Law observes that human perception scales as the logar...
research
01/26/2022

Probe-Based Interventions for Modifying Agent Behavior

Neural nets are powerful function approximators, but the behavior of a g...

Please sign up or login with your details

Forgot password? Click here to reset