DeepAI AI Chat
Log In Sign Up

A new Potential-Based Reward Shaping for Reinforcement Learning Agent

by   Babak Badnava, et al.

Potential-based reward shaping (PBRS) is a particular category of machine learning methods which aims to improve the learning speed of a reinforcement learning agent by extracting and utilizing extra knowledge while performing a task. There are two steps in the process of transfer learning: extracting knowledge from previously learned tasks and transferring that knowledge to use it in a target task. The latter step is well discussed in the literature with various methods being proposed for it, while the former has been explored less. With this in mind, the type of knowledge that is transmitted is very important and can lead to considerable improvement. Among the literature of both the transfer learning and the potential-based reward shaping, a subject that has never been addressed is the knowledge gathered during the learning process itself. In this paper, we presented a novel potential-based reward shaping method that attempted to extract knowledge from the learning process. The proposed method extracts knowledge from episodes' cumulative rewards. The proposed method has been evaluated in the Arcade learning environment and the results indicate an improvement in the learning process in both the single-task and the multi-task reinforcement learner agents.


page 1

page 2

page 3

page 4


Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning

Recent progress in deep model-based reinforcement learning allows agents...

Generic Itemset Mining Based on Reinforcement Learning

One of the biggest problems in itemset mining is the requirement of deve...

Transfer learning for process design with reinforcement learning

Process design is a creative task that is currently performed manually b...

Uniform State Abstraction For Reinforcement Learning

Potential Based Reward Shaping combined with a potential function based ...

Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks

This paper discusses a system that accelerates reinforcement learning by...

Biased Estimates of Advantages over Path Ensembles

The estimation of advantage is crucial for a number of reinforcement lea...

A Conceptual Framework for Externally-influenced Agents: An Assisted Reinforcement Learning Review

A long-term goal of reinforcement learning agents is to be able to perfo...