Many algorithms pass benchmarks, like navigation from a given location to a goal location in 3D games.
— Ida Momennejad (@criticalneuro) May 23, 2021
But passing benchmarks doesn't guarantee human-like navigation behavior nor cognitively or neurally plausible human-like algorithms/representations. This matters whether...2/n pic.twitter.com/0PM2yhvLWW
We used a modified version of a 4X4 player game by Ninja Theory, Bleeding Edge, for solo navigation.
— Ida Momennejad (@criticalneuro) May 23, 2021
The 3rd person perspective (camera following agent) allows us to observe how different algorithms learn to navigate to 16 goals & judge the human-likeness of their navigation
4/n pic.twitter.com/q3VNfHd5uw
Navigation Turing Test (NTT)
— Ida Momennejad (@criticalneuro) May 23, 2021
Once the agents were sufficiently trained, we designed 2 NTT studies in which we showed pairs of videos of agent vs. human navigation or pairs of 2 agents navigating the game.
Participants judged which of each pair's videos was played by a human
6/n pic.twitter.com/3ZxdPfFxcx
Eventually, we'd want algorithms that can judge human-likeness of artificial behavior rather than asking human participants, & one day meta-cognitively optimize behavior w these judgments.
— Ida Momennejad (@criticalneuro) May 23, 2021
So we compared a number of different architectures & inputs for artificial NTT judges
8/n pic.twitter.com/fyzJjUz8O0
Lessons:
— Ida Momennejad (@criticalneuro) May 23, 2021
- just passing navigation benchmarks doesn't lead to human-like nav
nor human-like algorithms or representations
- automated assessment of human-likeness of human vs agent easier than agent vs agent
- future work can study key behavioral features of human-like nav
10/n pic.twitter.com/GjLpyJgRwe
Toward these goals & inspired by meta-cognition in humans a future direction is to add in-built artificial judges of human-likeness that can flexibly modify and adapt parameters of the agent.
— Ida Momennejad (@criticalneuro) May 23, 2021
Building machines that learn to evaluate human-likeness can advance ML & cog neuro
12/n pic.twitter.com/59muMH5NX6
This assumes that such metacognition has enabled us humans to observe our own behavior, compare it with others' behavior, & flexibly adapt/adjust common human behaviors.
— Ida Momennejad (@criticalneuro) May 23, 2021
Speculation: could lead to RL/ML approaches to metacognition & social/cultural cog, & advance all 3.
n/n pic.twitter.com/uVzmTEJZn5
How does this bring any down to earth direction when imagining the real-life challenges most people face every day?
ReplyDeleteIt's only about getting from one physical place to another.
ReplyDelete