Relational Reinforcement Learning in Infinite Mario

02/28/2012
by   Shiwali Mohan, et al.
0

Relational representations in reinforcement learning allow for the use of structural information like the presence of objects and relationships between them in the description of value functions. Through this paper, we show that such representations allow for the inclusion of background knowledge that qualitatively describes a state and can be used to design agents that demonstrate learning behavior in domains with large state and actions spaces such as computer games.

READ FULL TEXT
03/23/2020

Incorporating Relational Background Knowledge into Reinforcement Learning via Differentiable Inductive Logic Programming

Relational Reinforcement Learning (RRL) can offers various desirable fea...
09/25/2020

Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks

We present a novel deep reinforcement learning framework for solving rel...
03/25/2022

Learning Relational Rules from Rewards

Humans perceive the world in terms of objects and relations between them...
06/09/2021

Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agents

Text-based games (TBGs) have become a popular proving ground for the dem...
10/30/2017

Eigenoption Discovery through the Deep Successor Representation

Options in reinforcement learning allow agents to hierarchically decompo...
12/12/2012

The Thing That We Tried Didn't Work Very Well : Deictic Representation in Reinforcement Learning

Most reinforcement learning methods operate on propositional representat...
02/15/2020

PDDLGym: Gym Environments from PDDL Problems

We present PDDLGym, a framework that automatically constructs OpenAI Gym...

Code Repositories

MarioSoar

Agents, Code for running Soar with Infinite Mario RL 2009


view repo