Challenging On Car Racing Problem from OpenAI gym
This is an incremental study comparing existing methods for a specific reinforcement learning benchmark, with implications for efficiency under limited hardware resources.
The authors tackled the continuous control task of the OpenAI Gym Car Racing problem by comparing a genetic multi-layer perceptron and double deep Q-learning, finding that the genetic method converges faster but deep Q-learning achieves better scores with more episodes.
This project challenges the car racing problem from OpenAI gym environment. The problem is very challenging since it requires computer to finish the continuous control task by learning from pixels. To tackle this challenging problem, we explored two approaches including evolutionary algorithm based genetic multi-layer perceptron and double deep Q-learning network. The result shows that the genetic multi-layer perceptron can converge fast but when training many episodes, double deep Q-learning can get better score. We analyze the result and draw a conclusion that for limited hardware resources, using genetic multi-layer perceptron sometimes can be more efficient.