Collaborating Authors

North Korean incomes improving but far below South

The Japan Times

SEOUL – North Koreans enjoyed the fastest improvement in their incomes in five years in 2016, according to South Korea's statistics agency, but people south of the DMZ are still more than 20 times better off.

Taylor Expansion Policy Optimization Machine Learning

In this work, we investigate the application of Taylor expansions in reinforcement learning. In particular, we propose Taylor expansion policy optimization, a policy optimization formalism that generalizes prior work (e.g., TRPO) as a first-order special case. We also show that Taylor expansions intimately relate to off-policy evaluation. Finally, we show that this new formulation entails modifications which improve the performance of several state-of-the-art distributed algorithms.

Partial-Expansion A* with Selective Node Generation

AAAI Conferences

A* is often described as being `optimal', in that it expands the minimum number of unique nodes. But, A* may generate many extra nodes which are never expanded. This is a performance loss, especially when the branching factor is large. Partial Expansion A* addresses this problem when expanding a node, n, by generating all the children of n but only storing children with the same f-cost as n. n is re-inserted into the OPEN list, but with the f-cost of the next best child. This paper introduces an enhanced version of PEA* (EPEA*). Given a priori domain knowledge, EPEA* generates only the children with the same f-cost as the parent. EPEA* is generalized to its iterative-deepening variant, EPE-IDA*. For some domains, these algorithms yield substantial performance improvements. State-of-the-art results were obtained for the pancake puzzle and for some multi-agent pathfinding instances. Drawbacks of EPEA* are also discussed.

UniAGENT: Reduced Time-Expansion Graphs and Goal Decomposition in Sub-optimal Cooperative Path Finding

AAAI Conferences

Solving cooperative path finding (CPF) by translating it to propositional satisfiability represents a viable option in highly constrained situations. The task in CPF is to relocate agents from their initial positions to given goals in a collision free manner. In this paper, we propose a reduced time expansion that is focused on makespan sub-optimal solving of the problem. The suggested reduced time expansion is especially beneficial in conjunction with a goal decomposition where agents are relocated one by one.

Apple plans expansion of artificial intelligence efforts in Seattle


Apple is planning an expansion of its Seattle operations, which primarily center on artificial intelligence and machine learning. The company is in the process of moving the engineering team from Turi, the AI-focused startup that the company acquired last year, into the Two Union Square skyscraper. Apple currently leases two floors of the building, and will lease more to accommodate its Seattle expansion. "We're trying to find the best people who are excited about AI and machine learning -- excited about research and thinking long term but also bringing those ideas into products that impact and delight our customers," said computer scientist Carlos Guestrin, Apple director of machine learning. "The bar is high, but we're going to be hiring as quickly as we can find people that meet our high bar, which is exciting."