GitHub / Hilton-AH / YODO-novel-RL-algorithm
Using DAgger with our MPC treated as the expert, we are able to effectively distill knowledge into relatively simple networks while still being able to retain a large fraction of the performance. (Please see paper for full description).
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hilton-AH%2FYODO-novel-RL-algorithm
PURL: pkg:github/Hilton-AH/YODO-novel-RL-algorithm
Stars: 0
Forks: 0
Open issues: 0
License: mit
Language: Jupyter Notebook
Size: 14.2 MB
Dependencies parsed at: Pending
Created at: almost 2 years ago
Updated at: almost 2 years ago
Pushed at: almost 2 years ago
Last synced at: over 1 year ago
Topics: dataset-aggregation, gym-environment, model-predictive-control, reinforcement-learning, robot-learning