An Approach to Partial Observability in Games: Learning to Both Act and Observe

08/11/2021
by   Elizabeth Gilmour, et al.
0

Reinforcement learning (RL) is successful at learning to play games where the entire environment is visible. However, RL approaches are challenged in complex games like Starcraft II and in real-world environments where the entire environment is not visible. In these more complex games with more limited visual information, agents must choose where to look and how to optimally use their limited visual information in order to succeed at the game. We verify that with a relatively simple model the agent can learn where to look in scenarios with a limited visual bandwidth. We develop a method for masking part of the environment in Atari games to force the RL agent to learn both where to look and how to play the game in order to study where the RL agent learns to look. In addition, we develop a neural network architecture and method for allowing the agent to choose where to look and what action to take in the Pong game. Further, we analyze the strategies the agent learns to better understand how the RL agent learns to play the game.

READ FULL TEXT

page 2

page 3

page 4

research
12/17/2016

Learning to predict where to look in interactive environments using deep recurrent q-learning

Bottom-Up (BU) saliency models do not perform well in complex interactiv...
research
11/24/2021

How does AI play football? An analysis of RL and real-world football strategies

Recent advances in reinforcement learning (RL) have made it possible to ...
research
03/13/2021

Network Environment Design for Autonomous Cyberdefense

Reinforcement learning (RL) has been demonstrated suitable to develop ag...
research
05/24/2023

SPRING: GPT-4 Out-performs RL Algorithms by Studying Papers and Reasoning

Open-world survival games pose significant challenges for AI algorithms ...
research
06/29/2018

Counting to Explore and Generalize in Text-based Games

We propose a recurrent RL agent with an episodic exploration mechanism t...
research
05/12/2023

Mastering Percolation-like Games with Deep Learning

Though robustness of networks to random attacks has been widely studied,...
research
05/25/2020

Learning to Simulate Dynamic Environments with GameGAN

Simulation is a crucial component of any robotic system. In order to sim...

Please sign up or login with your details

Forgot password? Click here to reset