DeepAI AI Chat
Log In Sign Up

Generalization of Agent Behavior through Explicit Representation of Context

06/18/2020
by   Cem C. Tutum, et al.
0

In order to deploy autonomous agents in digital interactive environments, they must be able to act robustly in unseen situations. The standard machine learning approach is to include as much variation as possible into training these agents. The agents can then interpolate within their training, but they cannot extrapolate much beyond it. This paper proposes a principled approach where a context module is coevolved with a skill module in the game. The context module recognizes the temporal variation in the game and modulates the outputs of the skill module so that the action decisions can be made robustly even in previously unseen situations. The approach is evaluated in the Flappy Bird and LunarLander video games, as well as in the CARLA autonomous driving simulation. The Context+Skill approach leads to significantly more robust behavior in environments that require extrapolation beyond training. Such a principled generalization ability is essential in deploying autonomous agents in real-world tasks, and can serve as a foundation for continual adaptation as well.

READ FULL TEXT

page 2

page 4

page 6

02/13/2020

Adapting to Unseen Environments through Explicit Representation of Context

In order to deploy autonomous agents to domains such as autonomous drivi...
04/18/2023

Assessing Video Game Balance using Autonomous Agents

As the complexity and scope of games increase, game testing, also called...
10/25/2021

What Would Jiminy Cricket Do? Towards Agents That Behave Morally

When making everyday decisions, people are guided by their conscience, a...
07/19/2021

Hierarchical Few-Shot Imitation with Skill Transition Models

A desirable property of autonomous agents is the ability to both solve l...
12/09/2021

Learning Generalizable Behavior via Visual Rewrite Rules

Though deep reinforcement learning agents have achieved unprecedented su...
05/19/2023

The Waymo Open Sim Agents Challenge

In this work, we define the Waymo Open Sim Agents Challenge (WOSAC). Sim...
05/25/2020

Learning to Simulate Dynamic Environments with GameGAN

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