Fetching the paper…

Reading the bibliography…

2017

Pragmatic-Pedagogic Value Alignment

Fisac, Jaime F., Gates, Monica A., Hamrick, Jessica B. et al.

Original
PDF
Post on X

Understand

As intelligent systems gain autonomy and capability, it becomes vital to ensure that their objectives match those of their human users; this is known as the value-alignment problem.

In robotics, value alignment is key to the design of collaborative robots that can integrate into human workflows, successfully inferring and adapting to their users' objectives as they go.
We argue that a meaningful solution to value alignment must combine multi-agent decision theory with rich mathematical models of human cognition, enabling robots to tap into people's natural collaborative capabilities.
We present a solution to the cooperative inverse reinforcement learning (CIRL) dynamic game based on well-established cognitive models of decision making and theory of mind.

Pragmatic-Pedagogic Value Alignment · Around

Built on

“An Experimental Study of Apparent Behavior”
Fritz Heider and Marianne Simmel · 1944
Earlier work this paper cites.
“Individual Choice Behavior: a Theoretical Analysis”
R. Luce · 1959
Earlier work this paper cites.
“The strategy of conflict”
Thomas Schelling · 1960
Earlier work this paper cites.
“Judgment under Uncertainty: Heuristics and Biases”
Amos Tversky and Daniel Kahneman · 1974
Earlier work this paper cites.
“Understanding the intentions of others: Re-enactment of intended acts by 18-month-old children.”
Andrew. Meltzoff · 1995
Earlier work this paper cites.

Similar

“Complexity of Finite-horizon Markov Decision Process Problems”
Martin Mundhenk, Judy Goldsmith, Christopher Lusena and Eric Allender · 2000
Cited alongside, same era.
“Monte-Carlo Planning in Large POMDPs”
David Silver and Joel Veness · 2010
Cited alongside, same era.
“Bayesian games: Games with incomplete information”
Shmuel Zamir · 2012
Cited alongside, same era.
“A rational account of pedagogical reasoning: Teaching by, and learning from, examples”
Patrick Shafto, Noah. Goodman and Thomas. Griffiths · 2013
Cited alongside, same era.

Then

“Modeling Human Plan Recognition Using Bayesian Theory of Mind”
Chris. Baker and Joshua. Tenenbaum · 2014
Later among the works it cites.
“Integrating human observer inferences into robot motion planning”
Anca.. Dragan and Siddhartha Srinivasa · 2014
Later among the works it cites.
“Cooperative Inverse Reinforcement Learning”
Dylan Hadfield-Menell, Anca Dragan, Pieter Abbeel and Stuart Russell · 2016
Later among the works it cites.
“Concrete Problems in AI Safety”
Original
Dario Amodei, Jacob Steinhardt, Dan Man and Paul Christiano · 2017
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…