2017 · 79 citations · 3 references
ComputingAutonomous SystemsComputer ScienceArtificial IntelligenceAutonomous VehiclesMachine LearningDeep LearningLearning From DemonstrationPolicy LearningReinforcement LearningTrajectory PredictionVehicle ControlAgent Reinforcement LearningDeep Reinforcement LearningReinforcement Learning For RoboticsReward Function DesignVisuomotor Policy Learning
We address the problem of autonomous race car driving. Using a recent rally game (WRC6) with realistic physics and graphics we train an Asynchronous Actor Critic (A3C) in an end-to-end fashion and propose an improved reward function to learn faster. The network is trained simultaneously on three very different tracks (snow, mountain, and coast) with various road structures, graphics and physics. Despite the more complex environments the trained agent learns significant features and exhibits good performance while driving in a more stable way than existing end-to-end approaches.
3
DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving
Chenyi Chen, Ari Seff, Alain L. Kornhauser et al. · 2015 · 1.8K citations
End-to-end training of deep visuomotor policies
Sergey Levine, Chelsea Finn, Trevor Darrell et al. · Journal of Machine Learning Research · 2016 · 1.7K citations
ViZDoom: A Doom-based AI research platform for visual reinforcement learning
Michał Kempka, Marek Wydmuch, Grzegorz Runc et al. · 2016 · 199 citations · Full text