We describe a computer system that provides a real-time musi(cid:173) cal accompaniment for a live soloist in a piece of non-improvised music for soloist and accompaniment. A Bayesian network is devel(cid:173) oped that represents the joint distribution on the times at which the solo and accompaniment notes are played, relating the two parts through a layer of hidden variables. The network is first con(cid:173) structed using the rhythmic information contained in the musical score. The network is then trained to capture the musical interpre(cid:173) tations of the soloist and accompanist in an off-line rehearsal phase. During live accompaniment the learned distribution of the network is combined with a real-time analysis of the soloist's acoustic sig(cid:173) nal, performed with a hidden Markov model, to generate a musi(cid:173) cally principled accompaniment that respects all available sources of knowledge.

It don't mean a thing if it ain't got that swing, but so far it has been difficult for jazz musicians to actually define what'swing' is. Scientists at the Max Planck Institute for Dynamics and Self-Organization in Germany think they have found out, after their study revealed that the rhythm is the result of micro-delays in musical timing. Traditionally, swing is thought to be added to a piece of music when quavers - notes that are an eighth of the duration of a whole note - are played with uneven lengths. The researchers played manipulated pieces of music to jazz musicians, to see if changes in timing affected their perception of its swing. It was found that when the notes on beat one and three were delayed by 30 milliseconds, the musicians were 7.48 times more likely to rate the music as having more swing. However, the microtiming deviations were so small that they were imperceptible to professional jazz musicians, suggesting they use them unconsciously.

This paper presents a new method SOLOIST, which uses transfer learning to efficiently build task-oriented dialog systems at scale. We parameterize a dialog system using a Transformer-based auto-regressive language model, which subsumes different dialog modules (e.g., state tracker, dialog policy, response generator) into a single neural model. We pre-train, on large heterogeneous dialog corpora, a large-scale Transformer model which can generate dialog responses grounded in user goals and real-world knowledge for task completion. The pre-trained model can be efficiently adapted to accomplish a new dialog task with a handful of task-specific dialogs via machine teaching. Our experiments demonstrate that (i) SOLOIST creates new state-of-the-art results on two well-known benchmarks, CamRest and MultiWOZ, (ii) in the few-shot learning setting, the dialog systems developed by SOLOIST significantly outperform those developed by existing methods, and (iii) the use of machine teaching substantially reduces the labeling cost. We will release our code and pre-trained models for reproducible research.

Trick-taking card games feature a large amount of private information that slowly gets revealed through a long sequence of actions. This makes the number of histories exponentially large in the action sequence length, as well as creating extremely large information sets. As a result, these games become too large to solve. To deal with these issues many algorithms employ inference, the estimation of the probability of states within an information set. In this paper, we demonstrate a Policy Based Inference (PI) algorithm that uses player modelling to infer the probability we are in a given state. We perform experiments in the German trick-taking card game Skat, in which we show that this method vastly improves the inference as compared to previous work, and increases the performance of the state-of-the-art Skat AI system Kermit when it is employed into its determinized search algorithm.

Decision-making in large imperfect information games is difficult. Thanks to recent success in Poker, Counterfactual Regret Minimization (CFR) methods have been at the forefront of research in these games. However, most of the success in large games comes with the use of a forward model and powerful state abstractions. In trick-taking card games like Bridge or Skat, large information sets and an inability to advance the simulation without fully determinizing the state make forward search problematic. Furthermore, state abstractions can be especially difficult to construct because the precise holdings of each player directly impact move values. In this paper we explore learning model-free policies for Skat from human game data using deep neural networks (DNN). We produce a new state-of-the-art system for bidding and game declaration by introducing methods to a) directly vary the aggressiveness of the bidder and b) declare games based on expected value while mitigating issues with rarely observed state-action pairs. Although cardplay policies learned through imitation are slightly weaker than the current best search-based method, they run orders of magnitude faster. We also explore how these policies could be learned directly from experience in a reinforcement learning setting and discuss the value of incorporating human data for this task.

In trick-taking card games, a two-step process of state sampling and evaluation is widely used to approximate move values. While the evaluation component is vital, the accuracy of move value estimates is also fundamentally linked to how well the sampling distribution corresponds the true distribution. Despite this, recent work in trick-taking card game AI has mainly focused on improving evaluation algorithms with limited work on improving sampling. In this paper, we focus on the effect of sampling on the strength of a player and propose a novel method of sampling more realistic states given move history. In particular, we use predictions about locations of individual cards made by a deep neural network --- trained on data from human gameplay - in order to sample likely worlds for evaluation. This technique, used in conjunction with Perfect Information Monte Carlo (PIMC) search, provides a substantial increase in cardplay strength in the popular trick-taking card game of Skat.

For the first Green Umbrella program of the season, Saturday night at Walt Disney Concert Hall, John Adams conducted the Los Angeles Philharmonic New Music Group in five premieres -- four of them commissioned by the orchestra, including one by 17-year-old clarinetist Andrew Moses and another by Ingram Marshall, 74 and in too poor of health to have attended, whose "Flow" is special enough that it deserves to bring lasting glory to the orchestra. But because I didn't want Marshall's piece to get lost in a big evening, I've buried the lead: The New Music Group was followed by a late-night appearance of wild Up, with Christopher Rountree conducting his increasingly impressive young ensemble in three more premieres. One was his own dazzling violin concert featuring Jennifer Koh as soloist, yet another L.A. Phil commission. Exiting the Grand Avenue staircase close to midnight, we were given bells for audience participation in still another L.A. Phil-commissioned world premiere, this by the collective Lucky Dragons. Even with all that, I've buried the lead, again.

As adversarial environments become more complex, it is increasingly crucial for agents to exploit the mistakes of weaker opponents, particularly in the context of winning tournaments and competitions.In this work, we present a simple post processing technique, which wecall Perfect Information Post-Mortem Analysis (PIPMA), that can quickly assess the playing strength of an opponent in certain classes of game environments. We apply this technique to skat, a popular German card game, and show that we can achieve substantial performance gains against not only players weaker than our program, but against stronger players as well. Most importantly, PIPMA can model the opponent after only a handful of games. To our knowledge, this makes our work the first successful example of an opponent modelling technique that can adapt its play to a particular opponent in real time in a complex game setting.