- TORCS is a continuous control problem. DQN works only for discrete actions, and so it cannot be used in TORCS.
- The initialization is another initialization strategy; you can also use a random uniform initialization with the min and max values of the range specified; another approach is to sample from a Gaussian with a zero mean and a specified sigma value. The interested reader must try these different initializers and compare the agent's performance.
- The abs() function is used in the reward function, as we penalize lateral drift from the center equally on either side (left or right). The first term is the longitudinal speed, and so no abs() function is required.
- The Gaussian noise added to the actions for exploration can be tapered down with episode count, and this can result in smoother driving. Surely, there are many other tricks you can do!
- DDPG is off-policy...
- Tech Categories
- Best Sellers
- New Releases
- Books
- Videos
- Audiobooks
Tech Categories Popular Audiobooks
- Articles
- Newsletters
- Free Learning
You're reading from TensorFlow Reinforcement Learning Quick Start Guide
Kaushik Balakrishnan works for BMW in Silicon Valley, and applies reinforcement learning, machine learning, and computer vision to solve problems in autonomous driving. Previously, he also worked at Ford Motor Company and NASA Jet Propulsion Laboratory. His primary expertise is in machine learning, computer vision, and high-performance computing, and he has worked on several projects involving both research and industrial applications. He has also worked on numerical simulations of rocket landings on planetary surfaces, and for this he developed several high-fidelity models that run efficiently on supercomputers. He holds a PhD in aerospace engineering from the Georgia Institute of Technology in Atlanta, Georgia.
Read more about Kaushik Balakrishnan
Unlock this book and the full library FREE for 7 days
Author (1)
Kaushik Balakrishnan works for BMW in Silicon Valley, and applies reinforcement learning, machine learning, and computer vision to solve problems in autonomous driving. Previously, he also worked at Ford Motor Company and NASA Jet Propulsion Laboratory. His primary expertise is in machine learning, computer vision, and high-performance computing, and he has worked on several projects involving both research and industrial applications. He has also worked on numerical simulations of rocket landings on planetary surfaces, and for this he developed several high-fidelity models that run efficiently on supercomputers. He holds a PhD in aerospace engineering from the Georgia Institute of Technology in Atlanta, Georgia.
Read more about Kaushik Balakrishnan