In order to maintain their performance in a dynamic environment, agents may be required to modify their learning behavior during run-time. If an agent utilizes a rule-based system...
Stephen Quirolgico, K. Canfield, Timothy W. Finin,...
In reinforcement learning, an agent tries to learn a policy, i.e., how to select an action in a given state of the environment, so that it maximizes the total amount of reward it ...
We propose CCRank, the first parallel algorithm for learning to rank, targeting simultaneous improvement in learning accuracy and efficiency. CCRank is based on cooperative coev...
Shuaiqiang Wang, Byron J. Gao, Ke Wang, Hady Wiraw...
Effective norms, emerging from sustained individual interactions over time, can complement societal rules and significantly enhance performance of individual agents and agent soci...
In the Markov decision process (MDP) formalization of reinforcement learning, a single adaptive agent interacts with an environment defined by a probabilistic transition function....