DeepAI AI Chat
Log In Sign Up

Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?

by   Xue Bin Peng, et al.
The University of British Columbia

The use of deep reinforcement learning allows for high-dimensional state descriptors, but little is known about how the choice of action representation impacts the learning difficulty and the resulting performance. We compare the impact of four different action parameterizations (torques, muscle-activations, target joint angles, and target joint-angle velocities) in terms of learning time, policy robustness, motion quality, and policy query rates. Our results are evaluated on a gait-cycle imitation task for multiple planar articulated figures and multiple gaits. We demonstrate that the local feedback provided by higher-level action parameterizations can significantly impact the learning, robustness, and quality of the resulting policies.


page 1

page 2

page 3

page 4


Advanced Skills by Learning Locomotion and Local Navigation End-to-End

The common approach for local navigation on challenging environments wit...

A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation

Marginalized importance sampling (MIS), which measures the density ratio...

Enhancing Efficiency of Quadrupedal Locomotion over Challenging Terrains with Extensible Feet

Recent advancements in legged locomotion research have made legged robot...

Randomized Policy Learning for Continuous State and Action MDPs

Deep reinforcement learning methods have achieved state-of-the-art resul...

Learning Variable Impedance Control for Contact Sensitive Tasks

Reinforcement learning algorithms have shown great success in solving di...

Cell Selection with Deep Reinforcement Learning in Sparse Mobile Crowdsensing

Sparse Mobile CrowdSensing (MCS) is a novel MCS paradigm where data infe...