Realistic domains for learning possess regularities that make it possible to generalize experience across related states. This paper explores an environment-modeling framework tha...
- Managing the product’s backlog is a major task in agile projects. This case study reports on one organization’s experiences from the transition to a backlog management tool a...
Potential-based shaping was designed as a way of introducing background knowledge into model-free reinforcement-learning algorithms. By identifying states that are likely to have ...
In packet switches, packets queue at switch inputs and contend for outputs. The contention arbitration policy directly affects switch performance. The best policy depends on the c...
We introduce a model of mutually attracting agents in an arbitrary network, for which the long term behavior results in the emergence of several clusters. The cluster structure is ...