Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments

by   Łukasz Kidziński, et al.

In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle course. Top participants were invited to describe their algorithms. In this work, we present eight solutions that used deep reinforcement learning approaches, based on algorithms such as Deep Deterministic Policy Gradient, Proximal Policy Optimization, and Trust Region Policy Optimization. Many solutions use similar relaxations and heuristics, such as reward shaping, frame skipping, discretization of the action space, symmetry, and policy blending. However, each of the eight teams implemented different modifications of the known algorithms.


page 13

page 23

page 24


Artificial Intelligence for Prosthetics - challenge solutions

In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, p...

Run, skeleton, run: skeletal model in a physics-based simulation

In this paper, we present our approach to solve a physics-based reinforc...

Learning to Run challenge: Synthesizing physiologically accurate motion using deep reinforcement learning

Synthesizing physiologically-accurate human movement in a variety of con...

Natural Policy Gradients In Reinforcement Learning Explained

Traditional policy gradient methods are fundamentally flawed. Natural gr...

Deep Reinforcement Learning for Stock Portfolio Optimization

Stock portfolio optimization is the process of constant re-distribution ...

Obstacle Avoidance and Navigation Utilizing Reinforcement Learning with Reward Shaping

In this paper, we investigate the obstacle avoidance and navigation prob...

Taylor Expansion Policy Optimization

In this work, we investigate the application of Taylor expansions in rei...

Please sign up or login with your details

Forgot password? Click here to reset