Artificial Intelligence for Prosthetics - challenge solutions

by   Łukasz Kidziński, et al.

In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector. Top participants were invited to describe their algorithms. In this work, we describe the challenge and present thirteen solutions that used deep reinforcement learning approaches. Many solutions use similar relaxations and heuristics, such as reward shaping, frame skipping, discretization of the action space, symmetry, and policy blending. However, each team implemented different modifications of the known algorithms by, for example, dividing the task into subtasks, learning low-level control, or by incorporating expert knowledge and using imitation learning.


Fuzzy Controller of Reward of Reinforcement Learning For Handwritten Digit Recognition

Recognition of human environment with computer systems always was a big ...

ProLoNets: Neural-encoding Human Experts' Domain Knowledge to Warm Start Reinforcement Learning

Deep reinforcement learning has seen great success across a breadth of t...

Learning the aerodynamic design of supercritical airfoils through deep reinforcement learning

The aerodynamic design of modern civil aircraft requires a true sense of...

Reward is not enough: can we liberate AI from the reinforcement learning paradigm?

I present arguments against the hypothesis put forward by Silver, Singh,...

Towards sample-efficient episodic control with DAC-ML

The sample-inefficiency problem in Artificial Intelligence refers to the...

Please sign up or login with your details

Forgot password? Click here to reset