Online Evolution of Deep Convolutional Network for Vision-Based Reinforcement Learning

26 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Continuous control with deep reinforcement learning (2015, background): “On both low-dimensional and from pixels, some replicas were able to learn reasonable policies that are able to complete a circuit around the track though other replicas failed to learn a sensible policy.”
Human action recognition using genetic algorithms and convolutional neural networks (2016, methodology): “Koutnk et al. proposed an online evolutionary training algorithm [62] for driving a race car in TORCS racing simulator using recurrent neural network controller and max-pooling convolutional neural network for feature extraction.”
Teaching UAVs to Race: End-to-End Regression of Agile Controls in Simulation (2017, methodology): “Recently, TORCS has also been successfully used in several RL approaches for autonomous car driving [18, 21, 24]; however, in these cases, RL was used to teach the agent to drive specific tracks or all available tracks rather than learning to drive never before seen tracks.”
Learning Real-World Robot Policies by Dreaming (2018, background): “These works learn state representations from raw images, and allow control of the agents directly based on image inputs [1], [12], [13], [14].”