We present several new algorithms for multiagent reinforcement learning. A common feature of these algorithms is a parameterized, structured representation of a policy or value fu...
Carlos Guestrin, Michail G. Lagoudakis, Ronald Par...
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
Bayesian Reinforcement Learning has generated substantial interest recently, as it provides an elegant solution to the exploration-exploitation trade-off in reinforcement learning...
This paper presents CBRetaliate, an agent that combines Case-Based Reasoning (CBR) and Reinforcement Learning (RL) algorithms. Unlike most previous work where RL is used to improve...
Bryan Auslander, Stephen Lee-Urban, Chad Hogg, H&e...
In reinforcement learning, an agent interacting with its environment strives to learn a policy that specifies, for each state it may encounter, what action to take. Evolutionary c...