Short-Term Trajectory Planning in TORCS using Deep Reinforcement Learning
- 1 December 2020
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2020 IEEE Symposium Series on Computational Intelligence (SSCI)
- p. 2327-2334
- https://doi.org/10.1109/ssci47803.2020.9308138
Abstract
The applications of deep reinforcement learning to racing games so far struggled to reach a performance competitive with the state of the art in this field. Previous work, mainly focused on a low-level input design, show that artificial agents are able to learn to stay on track starting from no driving knowledge; however, the final performance is still far from those of competitive driving. The scope of this work is to investigate in which measure rising the abstraction level can help the learning process. Using The Open Racing Car Simulator (TORCS) environment and the Deep Deterministic Policy Gradients (DDPG) algorithm, we develop artificial agents, considering both numerical and visual inputs, based on deep neural networks. These agents learn to compute either a target point on track or, additionally, a correction to the target maximum speed at the current position, which are then provided as input to a low-level control logic. Our results show that our approach is able to achieve a fair performance, though extremely sensitive to the low-level logic. Further work is necessary in order to understand how to fully exploit a high-level control design.Keywords
This publication has 10 references indexed in Scilit:
- Deep Learning for Video Game PlayingIEEE Transactions on Games, 2019
- End-to-End Race Driving with Deep Reinforcement LearningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2018
- DeepDriving: Learning Affordance for Direct Perception in Autonomous DrivingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Human-level control through deep reinforcement learningNature, 2015
- The Arcade Learning Environment: An Evaluation Platform for General AgentsJournal of Artificial Intelligence Research, 2013
- Model-Free reinforcement learning with continuous action in practicePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- A human-like TORCS controller for the Simulated Car Racing ChampionshipPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- The 2009 Simulated Car Racing ChampionshipIEEE Transactions on Computational Intelligence and AI in Games, 2010
- A modular parametric architecture for the TORCS racing enginePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989