Neural reinforcement learning for behaviour synthesis

By Claude F. Touzet. 1997

How researchers see this paper

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

Citations in the corpus

Reinforcement learning in robotics: A survey (2013, methodology): “This approach was also used for a navigation and obstacle avoidance task with a mobile robot (Touzet, 1997).”
Multi-agent Reinforcement Learning: An Overview (2010, methodology): “Q-learning has been combined with Q-function approximators relying on, e.g., basis-function representations [110,121], neural networks and self-organizing maps [127], and fuzzy rule bases [41,47,56].”
Application of reinforcement learning in robot soccer (2007, methodology): “The neural network (NN) and the fuzzy inference system (FIS) have the better approximate property (Zengqi, 2000; Bonissone and Piero, 1995; Claude, 1997).”
Reinforcement Learning in Continuous State and Action Spaces (2012, unknown): “Examples include Backgammon (Tesauro, 1992, 1994, 1995), robotics (Anderson, 1989; Lin, 1993; Touzet, 1997; Coulom, 2002) and elevator dispatching (Crites and Barto, 1996, 1998).”
A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems (2010, background): “cially, as a result of their adaptability, ANN represent powerful solutions for subjective information processing [22], decision-making [23], forecasting [24] and related problems which became during the last decades central points of an ever-increasing range of real-world and industrial application”
Reinforcement Learning: an Overview (2000, background): “• In spite of its very intuitive aspect, it exists situations where the function of reinforcement is difficult to design [30].”