Artificial Intelligence

---

Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog (1907.00456v2)

Natasha Jaques, Asma Ghandeharioun, Judy Hanwen Shen, Craig Ferguson, Agata Lapedriza, Noah Jones, Shixiang Gu, Rosalind Picard

2019-06-30

Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment. These are critical shortcomings for applying RL to real-world problems where collecting data is expensive, and models must be tested offline before being deployed to interact with the environment -- e.g. systems that learn from human interaction. Thus, we develop a novel class of off-policy batch RL algorithms, which are able to effectively learn offline, without exploring, from a fixed batch of human interaction data. We leverage models pre-trained on data as a strong prior, and use KL-control to penalize divergence from this prior during RL training. We also use dropout-based uncertainty estimates to lower bound the target Q-values as a more efficient alternative to Double Q-Learning. The algorithms are tested on the problem of open-domain dialog generation -- a challenging reinforcement learning problem with a 20,000-dimensional action space. Using our Way Off-Policy algorithm, we can extract multiple different reward functions post-hoc from collected human interaction data, and learn effectively from all of these. We test the real-world generalization of these systems by deploying them live to converse with humans in an open-domain setting, and demonstrate that our algorithm achieves significant improvements over prior methods in off-policy batch RL.

Observing the LOD Cloud using Equivalent Set Graphs: the LOD Cloud is mostly flat and sparsely linked (1906.08097v2)

Luigi Asprino, Wouter Beek, Paolo Ciancarini, Frank van Harmelen, Valentina Presutti

2019-06-19

This paper presents an empirical study aiming at understanding the modeling style and the overall semantic structure of Linked Open Data. We observe how classes, properties and individuals are used in practice. We also investigate how hierarchies of concepts are structured, and how much they are linked. In addition to discussing the results, this paper contributes (i) a conceptual framework, including a set of metrics, which generalises over the observable constructs; (ii) an open source implementation that facilitates its application to other Linked Data knowledge graphs.

Deep Reinforcement Learning for Unmanned Aerial Vehicle-Assisted Vehicular Networks in Smart Cities (1906.05015v4)

Ming Zhu, Xiao-Yang Liu, Xiaodong Wang

2019-06-12

Unmanned aerial vehicles (UAVs) are envisioned to complement the 5G communication infrastructure in future smart cities. Hot spots easily appear in road intersections, where effective communication among vehicles is challenging. UAVs may serve as relays with the advantages of low price, easy deployment, line-of-sight links, and flexible mobility. In this paper, we study a UAV-assisted vehicular network where the UAV jointly adjusts its transmission power and bandwidth allocation under 3D flight to maximize the total throughput. First, we formulate a Markov Decision Process (MDP) problem by modeling the mobility of the UAV/vehicles and the state transitions. Secondly, we solve the target problem using a deep reinforcement learning method, namely, the deep deterministic policy gradient, and propose three solutions with different control objectives. Then we extend the proposed solutions considering of the energy consumption of 3D flight. Thirdly, in a simplified model with small state space and action space, we verify the optimality of proposed algorithms. Comparing with two baseline schemes, we demonstrate the effectiveness of proposed algorithms in a realistic model.

General non-linear Bellman equations (1907.03687v1)

Hado van Hasselt, John Quan, Matteo Hessel, Zhongwen Xu, Diana Borsa, Andre Barreto

2019-07-08

We consider a general class of non-linear Bellman equations. These open up a design space of algorithms that have interesting properties, which has two potential advantages. First, we can perhaps better model natural phenomena. For instance, hyperbolic discounting has been proposed as a mathematical model that matches human and animal data well, and can therefore be used to explain preference orderings. We present a different mathematical model that matches the same data, but that makes very different predictions under other circumstances. Second, the larger design space can perhaps lead to algorithms that perform better, similar to how discount factors are often used in practice even when the true objective is undiscounted. We show that many of the resulting Bellman operators still converge to a fixed point, and therefore that the resulting algorithms are reasonable and inherit many beneficial properties of their linear counterparts.

An intelligent financial portfolio trading strategy using deep Q-learning (1907.03665v1)

Hyungjun Park, Min Kyu Sim, Dong Gu Choi

2019-07-08

A goal of financial portfolio trading is maximizing the trader's utility by allocating capital to assets in a portfolio in the investment horizon. Our study suggests an approach for deriving an intelligent portfolio trading strategy using deep Q-learning. In this approach, we introduce a Markov decision process model to enable an agent to learn about the financial environment and develop a deep neural network structure to approximate a Q-function. In addition, we devise three techniques to derive a trading strategy that chooses reasonable actions and is applicable to the real world. First, the action space of the learning agent is modeled as an intuitive set of trading directions that can be carried out for individual assets in the portfolio. Second, we introduce a mapping function that can replace an infeasible agent action in each state with a similar and valuable action to derive a reasonable trading strategy. Last, we introduce a method by which an agent simulates all feasible actions and learns about these experiences to utilize the training data efficiently. To validate our approach, we conduct backtests for two representative portfolios, and we find that the intelligent strategy derived using our approach is superior to the benchmark strategies.

Do Transformer Attention Heads Provide Transparency in Abstractive Summarization? (1907.00570v2)

Joris Baan, Maartje ter Hoeve, Marlies van der Wees, Anne Schuth, Maarten de Rijke

2019-07-01

Learning algorithms become more powerful, often at the cost of increased complexity. In response, the demand for algorithms to be transparent is growing. In NLP tasks, attention distributions learned by attention-based deep learning models are used to gain insights in the models' behavior. To which extent is this perspective valid for all NLP tasks? We investigate whether distributions calculated by different attention heads in a transformer architecture can be used to improve transparency in the task of abstractive summarization. To this end, we present both a qualitative and quantitative analysis to investigate the behavior of the attention heads. We show that some attention heads indeed specialize towards syntactically and semantically distinct input. We propose an approach to evaluate to which extent the Transformer model relies on specifically learned attention distributions. We also discuss what this implies for using attention distributions as a means of transparency.

Data Efficient Reinforcement Learning for Legged Robots (1907.03613v1)

Yuxiang Yang, Ken Caluwaerts, Atil Iscen, Tingnan Zhang, Jie Tan, Vikas Sindhwani

2019-07-08

We present a model-based framework for robot locomotion that achieves walking based on only 4.5 minutes (45,000 control steps) of data collected on a quadruped robot. To accurately model the robot's dynamics over a long horizon, we introduce a loss function that tracks the model's prediction over multiple timesteps. We adapt model predictive control to account for planning latency, which allows the learned model to be used for real time control. Additionally, to ensure safe exploration during model learning, we embed prior knowledge of leg trajectories into the action space. The resulting system achieves fast and robust locomotion. Unlike model-free methods, which optimize for a particular task, our planner can use the same learned dynamics for various tasks, simply by changing the reward function. To the best of our knowledge, our approach is more than an order of magnitude more sample efficient than current model-free methods.

ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning (1907.03540v1)

Łukasz Dudziak, Mohamed S. Abdelfattah, Ravichander Vipperla, Stefanos Laskaridis, Nicholas D. Lane

2019-07-08

End-to-end automatic speech recognition (ASR) models are increasingly large and complex to achieve the best possible accuracy. In this paper, we build an AutoML system that uses reinforcement learning (RL) to optimize the per-layer compression ratios when applied to a state-of-the-art attention based end-to-end ASR model composed of several LSTM layers. We use singular value decomposition (SVD) low-rank matrix factorization as the compression method. For our RL-based AutoML system, we focus on practical considerations such as the choice of the reward/punishment functions, the formation of an effective search space, and the creation of a representative but small data set for quick evaluation between search steps. Finally, we present accuracy results on LibriSpeech of the model compressed by our AutoML system, and we compare it to manually-compressed models. Our results show that in the absence of retraining our RL-based search is an effective and practical method to compress a production-grade ASR system. When retraining is possible, we show that our AutoML system can select better highly-compressed seed models compared to manually hand-crafted rank selection, thus allowing for more compression than previously possible.

A unified decision making framework for supply and demand management in microgrid networks (1711.05078v2)

Diddigi Raghuram Bharadwaj, Sai Koti Reddy Danda, Krishnasuri Narayanam, Shalabh Bhatnagar

2017-11-14

This paper considers two important problems -- on the supply-side and demand-side respectively and studies both in a unified framework. On the supply side, we study the problem of energy sharing among microgrids with the goal of maximizing profit obtained from selling power while at the same time not deviating much from the customer demand. On the other hand, under shortage of power, this problem becomes one of deciding the amount of power to be bought with dynamically varying prices. On the demand side, we consider the problem of optimally scheduling the time-adjustable demand - i.e., of loads with flexible time windows in which they can be scheduled. While previous works have treated these two problems in isolation, we combine these problems together and provide a unified Markov decision process (MDP) framework for these problems. We then apply the Q-learning algorithm, a popular model-free reinforcement learning technique, to obtain the optimal policy. Through simulations, we show that the policy obtained by solving our MDP model provides more profit to the microgrids.

MDE: Multi Distance Embeddings for Link Prediction in Knowledge Graphs (1905.10702v7)

Afshin Sadeghi, Damien Graux, Hamed Shariat Yazdi, Jens Lehmann

2019-05-25

Over the past decade, knowledge graphs became popular for capturing structured domain knowledge. Relational learning models enable the prediction of missing links inside knowledge graphs. More specifically, latent distance approaches model the relationships among entities via a distance between latent representations. Translating embedding models (e.g., TransE) are among the most popular latent distance approaches which use one distance function to learn multiple relation patterns. However, they are not capable of capturing symmetric relations. They also force relations with reflexive patterns to become symmetric and transitive. In order to improve distance based embedding, we propose multi-distance embeddings (MDE). Our solution is based on the idea that by learning independent embedding vectors for each entity and relation one can aggregate contrasting distance functions. Benefiting from MDE, we also develop supplementary distances resolving the above-mentioned limitations of TransE. We further propose an extended loss function for distance based embeddings and show that MDE and TransE are fully expressive using this loss function. Furthermore, we obtain a bound on the size of their embeddings for full expressivity. Our empirical results show that MDE significantly improves the translating embeddings and outperforms several state-of-the-art embedding models on benchmark datasets.

---