This paper analyzes the complexity of on-line reinforcement learning algorithms, namely asynchronous realtime versions of Q-learning and value-iteration, applied to the problem of...
Two variable metric reinforcement learning methods, the natural actor-critic algorithm and the covariance matrix adaptation evolution strategy, are compared on a conceptual level a...
We present the first large-scale empirical application of reinforcement learning to the important problem of optimized trade execution in modern financial markets. Our experiments...
A key component of any reinforcement learning algorithm is the underlying representation used by the agent. While reinforcement learning (RL) agents have typically relied on hand-...
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...