Can reinforcement learning learn itself? A reply to 'Reward is enough'

Cifma (2021)
  Copy   BIBTEX

Abstract

In their paper 'Reward is enough', Silver et al conjecture that the creation of sufficiently good reinforcement learning (RL) agents is a path to artificial general intelligence (AGI). We consider one aspect of intelligence Silver et al did not consider in their paper, namely, that aspect of intelligence involved in designing RL agents. If that is within human reach, then it should also be within AGI's reach. This raises the question: is there an RL environment which incentivises RL agents to design RL agents?

Categories

Keywords

Reprint years

Links

PhilArchive

External links

  • This entry has no external links. Add one.
Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

My notes

Similar books and articles

The Archimedean trap: Why traditional reinforcement learning will probably not yield AGI.Samuel Allen Alexander - 2020 - Journal of Artificial General Intelligence 11 (1):70-85.
Reinforcement learning: A brief guide for philosophers of mind.Julia Haas - 2022 - Philosophy Compass 17 (9):e12865.
The relation of secondary reward to gradients of reinforcement.Charles C. Perkins Jr - 1947 - Journal of Experimental Psychology 37 (5):377.
Reinforcement learning with limited reinforcement: Using Bayes risk for active learning in POMDPs.Finale Doshi-Velez, Joelle Pineau & Nicholas Roy - 2012 - Artificial Intelligence 187-188 (C):115-132.
Framing reinforcement learning from human reward: Reward positivity, temporal discounting, episodicity, and performance.W. Bradley Knox & Peter Stone - 2015 - Artificial Intelligence 225 (C):24-50.
Discrimination of the reward in learning with partial and continuous reinforcement.Stewart H. Hulse - 1962 - Journal of Experimental Psychology 64 (3):227.
Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective.Tom Everitt, Marcus Hutter, Ramana Kumar & Victoria Krakovna - 2021 - Synthese 198 (Suppl 27):6435-6467.
Model-based average reward reinforcement learning.Prasad Tadepalli & DoKyeong Ok - 1998 - Artificial Intelligence 100 (1-2):177-224.
The relation of secondary reinforcement to delayed reward in visual discrimination learning.G. Robert Grice - 1948 - Journal of Experimental Psychology 38 (1):1.
Anticipation of reward as a function of partial reinforcement.Howard Brand, Paul J. Woods & James M. Sakoda - 1956 - Journal of Experimental Psychology 52 (1):18.
The role of secondary reinforcement in a partial reinforcement learning situation.M. R. Denny - 1946 - Journal of Experimental Psychology 36 (5):373.
Emotional State and Feedback-Related Negativity Induced by Positive, Negative, and Combined Reinforcement.Shuyuan Xu, Yuyan Sun, Min Huang, Yanhong Huang, Jing Han, Xuemei Tang & Wei Ren - 2021 - Frontiers in Psychology 12:647263.
Diversity of Developmental Trajectories in Natural and Artificial Intelligence.Aaron Sloman - unknown
SA w_ S _u: An Integrated Model of Associative and Reinforcement Learning.Vladislav D. Veksler, Christopher W. Myers & Kevin A. Gluck - 2014 - Cognitive Science 38 (3):580-598.
Generalized extinction and secondary reinforcement in visual discrimination learning with delayed reward.G. Robert Grice & Herbert M. Goldman - 1955 - Journal of Experimental Psychology 50 (3):197.

Analytics

Added to PP
2022-03-29

Downloads
1,195 (#10,179)

6 months
353 (#5,717)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Samuel Allen Alexander
Ohio State University (PhD)

Citations of this work

No citations found.

Add more citations

References found in this work

Reward is enough.David Silver, Satinder Singh, Doina Precup & Richard S. Sutton - 2021 - Artificial Intelligence 299 (C):103535.

View all 7 references / Add more references