Rule value reinforcement learning for cognitive agents

9 years 11 months ago
Rule value reinforcement learning for cognitive agents
RVRL (Rule Value Reinforcement Learning) is a new algorithm which extends an existing learning framework that models the environment of a situated agent using a probabilistic rule representation. The algorithm attaches values to learned rules by adapting reinforcement learning. Structure captured by the rules is used to form a policy. The resulting rule values represent the utility of taking an action if the rule's conditions are present in the agent's current percept. Advantages of the new framework are demonstrated, through examples in a predator-prey environment. Categories and Subject Descriptors I.2.1 [AI/GEN] General Terms Algorithms Keywords Reinforcement learning, perception, action, planning, situated agents, stochastic, environment, probabilistic logic.
Christopher Child, Kostas Stathis
Added 20 Aug 2010
Updated 20 Aug 2010
Type Conference
Year 2006
Where ATAL
Authors Christopher Child, Kostas Stathis
Comments (0)