AI Chat AI Image Generator AI Video Text to Speech

A Definition of Happiness for Reinforcement Learning Agents

05/18/2015

∙

by Mayank Daswani, et al.

∙

∙

What is happiness for reinforcement learning agents? We seek a formal definition satisfying a list of desiderata. Our proposed definition of happiness is the temporal difference error, i.e. the difference between the value of the obtained reward and observation and the agent's expectation of this value. This definition satisfies most of our desiderata and is compatible with empirical research on humans. We state several implications and discuss examples.

Mayank Daswani
2 publications
Jan Leike
27 publications

page 1

page 2

page 3

page 4

research

∙ 06/03/2021

Hyperbolically-Discounted Reinforcement Learning on Reward-Punishment Framework

This paper proposes a new reinforcement learning with hyperbolic discoun...

0 Taisuke Kobayashi, et al. ∙

research

∙ 11/21/2022

Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback

An important goal in artificial intelligence is to create agents that ca...

0 Josh Abramson, et al. ∙

research

∙ 04/11/2019

Defence Efficiency

In order to automate actions, such as defences against network attacks, ...

0 Gleb Polevoy, et al. ∙

research

∙ 05/31/2018

Agents and Devices: A Relative Definition of Agency

According to Dennett, the same system may be described using a `physical...

0 Laurent Orseau, et al. ∙

research

∙ 01/22/2021

Theory of Mind for Deep Reinforcement Learning in Hanabi

The partially observable card game Hanabi has recently been proposed as ...

0 Andrew Fuchs, et al. ∙

research

∙ 06/09/2016

Cooperative Inverse Reinforcement Learning

For an autonomous system to be helpful to humans and to pose no unwarran...

0 Dylan Hadfield-Menell, et al. ∙

research

∙ 03/06/2021

Reinforcement Learning, Bit by Bit

Reinforcement learning agents have demonstrated remarkable achievements ...

0 Xiuyuan Lu, et al. ∙