Push Your ML Model to Top Speed (AWS DeepRacer)
summary
AWS DeepRacer session about improving reinforcement learning models for racing by using human analysis of RL training logs. It covers examining training logs to identify trends and tuning model and training parameters to boost performance and prepare for new race divisions in the 2021 DeepRacer League.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 1:58New DeepRacer competitions
- 3:26Basic reward function
- 6:19Steps parameter and progress
- 10:58Optimizing track with waypoints
- 14:09Advanced geometric calculations
- 17:43Analyzing training graphs
- 25:12Logs and Jupyter analysis
- 29:26Summary and resources
related talks
28mShift your ML model into overdrive with AWS DeepRacer analysis tools
30mShift your ML model into overdrive with AWS DeepRacer analysis tools
27mGet rolling with machine learning on AWS DeepRacer
28mShift your ML model into overdrive with AWS DeepRacer analysis tools
29mGet rolling with ML on AWS DeepRacer
37mAWS DeepRacer: Train, Evaluate, and Tune
30mStart your ML journey with AWS DeepRacer for public sector
24mGet Rolling on Machine Learning