Learning to overtake in TORCS using simple reinforcement learning

76 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.

Programmatically Interpretable Reinforcement Learning (2018, methodology): “T ORCS has been used extensively in AI research, for example in (Salem et al., 2017), (Koutn´ık et al., 2013), and (Loiacono et al., 2010) among others.”
Autonomous vehicle control via deep reinforcement learning (2017, methodology): “Examples of algorithms utilized in the environment are Monte Carlo tree search [17], evolutionary algorithms [18] and Q-learning [19].”
Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles (2020, methodology): “As an example, the Q-learning made in [72] is presented.”
A Survey of State-Action Representations for Autonomous Driving (2018, methodology): “Speci c manoeuvers can also be used in the presence of obstacles, such as a pass behavior learnt in (Pyeatt and Howe, 1998) and an overtake behavior in (Loiacono et al., 2010).”
Distributed Multiagent Coordinated Learning for Autonomous Driving in Highways Based on Dynamic Coordination Graphs (2020, methodology): “In Q-learning, learning rate α is 0.1, discount factor γ is 0.95 and the initial exploration rate ε is 0.1 with decaying to 0.9ε every 10 episodes.”