Domain-Independent Optimistic Initialization for Reinforcement Learning

10/16/2014
by   Marlos C. Machado, et al.
0

In Reinforcement Learning (RL), it is common to use optimistic initialization of value functions to encourage exploration. However, such an approach generally depends on the domain, viz., the scale of the rewards must be known, and the feature representation must have a constant norm. We present a simple approach that performs optimistic initialization with less dependence on the domain.

READ FULL TEXT

page 1

page 2

research
12/05/2019

Training Agents using Upside-Down Reinforcement Learning

Traditional Reinforcement Learning (RL) algorithms either predict reward...
research
11/03/2021

The effect of synaptic weight initialization in feature-based successor representation learning

After discovering place cells, the idea of the hippocampal (HPC) functio...
research
10/05/2017

Exploration in Feature Space for Reinforcement Learning

The infamous exploration-exploitation dilemma is one of the oldest and m...
research
07/31/2017

Advantages and Limitations of using Successor Features for Transfer in Reinforcement Learning

One question central to Reinforcement Learning is how to learn a feature...
research
08/24/2021

Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning

Encouraging exploration is a critical issue in deep reinforcement learni...
research
06/06/2019

Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP

The lottery ticket hypothesis proposes that over-parameterization of dee...
research
12/13/2022

Improving generalization in reinforcement learning through forked agents

An eco-system of agents each having their own policy with some, but limi...

Please sign up or login with your details

Forgot password? Click here to reset