With reinforcement learning, an agent could learn complex behaviors from highlevel abstractions of the task. However, exploration and reward shaping remained challenging for existing methods, especially in scenarios where the extrinsic feedback was sparse. Expert demonstrations have been investigated to solve these difficulties, but a tremendous number of high-quality demonstrations were usually required. In this work, an integrated policy gradient algorithm was proposed to boost exploration and facilitate intrinsic reward learning from only limited number of demonstrations. We achieved this by reformulating the original reward function with two additional terms, where the first term measured the Jensen-Shannon divergence between current policy and the expert's demonstrations, and the second term estimated the agent's uncertainty about the environment. The presented algorithm was evaluated by a range of simulated tasks with sparse extrinsic reward signals, where only one single demonstrated trajectory was provided to each task. Superior exploration efficiency and high average return were demonstrated in all tasks. Furthermore, it was found that the agent could imitate the expert's behavior and meanwhile sustain high return.

Rich empirical evidence has shown that visual object recognition in the brain is fast and effortless, with relevant brain signals reported to start as early as 80 ms. Here we study the time trajectory of the recognition process at the level of minimal recognizable images (termed MIRC). These are images that can be recognized reliably, but in which a minute change of the image (reduction by either size or resolution) has a drastic effect on recognition. Subjects were assigned to one of nine exposure conditions: 200, 500, 1000, 2000 ms with or without masking, as well as unlimited time. The subjects were not limited in time to respond after presentation. The results show that in the masked conditions, recognition rates develop gradually over an extended period, e.g. average of 18% for 200 ms exposure and 45% for 500 ms, increasing significantly with longer exposure even above 2 secs. When presented for unlimited time (until response), MIRC recognition rates were equivalent to the rates of full-object images presented for 50 ms followed by masking. What takes the brain so long to recognize such images? We discuss why processes involving eye-movements, perceptual decision-making and pattern completion are unlikely explanations. Alternatively, we hypothesize that MIRC recognition requires an extended top-down process complementing the feed-forward phase.

In this paper, we propose a deep convolutional recurrent neural network that predicts action sequences for task and motion planning (TAMP) from an initial scene image. Typical TAMP problems are formalized by combining reasoning on a symbolic, discrete level (e.g. first-order logic) with continuous motion planning such as nonlinear trajectory optimization. Due to the great combinatorial complexity of possible discrete action sequences, a large number of optimization/motion planning problems have to be solved to find a solution, which limits the scalability of these approaches. To circumvent this combinatorial complexity, we develop a neural network which, based on an initial image of the scene, directly predicts promising discrete action sequences such that ideally only one motion planning problem has to be solved to find a solution to the overall TAMP problem. A key aspect is that our method generalizes to scenes with many and varying number of objects, although being trained on only two objects at a time. This is possible by encoding the objects of the scene in images as input to the neural network, instead of a fixed feature vector. Results show runtime improvements of several magnitudes. Video: https://youtu.be/i8yyEbbvoEk

In this paper, we focus on the problem of stable prediction across unknown test data, where the test distribution is agnostic and might be totally different from the training one. In such a case, previous machine learning methods might exploit subtly spurious correlations in training data induced by non-causal variables for prediction. Those spurious correlations are changeable across data, leading to instability of prediction across data. By assuming the relationships between causal variables and response variable are invariant across data, to address this problem, we propose a conditional independence test based algorithm to separate those causal variables with a seed variable as priori, and adopt them for stable prediction. By assuming the independence between causal and non-causal variables, we show, both theoretically and with empirical experiments, that our algorithm can precisely separate causal and non-causal variables for stable prediction across test data. Extensive experiments on both synthetic and real-world datasets demonstrate that our algorithm outperforms state-of-the-art methods for stable prediction.

This study focuses on simultaneous decision making for stochastic multi-echelon inventory optimization problems. Mixed supply chain networks are considered that may contain assembly or distribution nodes, or both, and may use nonlinear cost structure. We present a framework which uses deep neural networks as agents responsible for finding order-up-to levels for any desired components of the general supply chain network. Agents simultaneously interact with the environment in an unsupervised manner to minimize total inventory cost. Not only does this study consider several decision-makers simultaneously for stages of a general supply chain network, but it also presents clear and interpretable order-up-to levels. First, we numerically show the effectiveness of the method by solving newsvendor and serial supply chain networks and compare the results with the available closed form solutions for these settings. Then, we investigate a mixed supply chain network and a more general case study. The findings indicate that the proposed method performs better in terms of objective function values and the number of interactions with the environment compared to alternatives. In addition, the method finds inventory policies similar to simple base-stock policies for general SCNs. Moreover, we generally notice that for echelons closer to the source, fixed optimal order-up-to levels can be considerably larger than the expected demands these echelons observe.

Agent-based Models (ABMs) are valuable tools for policy analysis. ABMs help analysts explore the emergent consequences of policy interventions in multi-agent decision-making settings. But the validity of inferences drawn from ABM explorations depends on the quality of the ABM agents' behavioral models. Standard specifications of agent behavioral models rely either on heuristic decision-making rules or on regressions trained on past data. Both prior specification modes have limitations. This paper examines the value of reinforcement learning (RL) models as adaptive, high-performing, and behaviorally-valid models of agent decision-making in ABMs. We test the hypothesis that RL agents are effective as utility-maximizing agents in policy ABMs. We also address the problem of adapting RL algorithms to handle multi-agency in games by adapting and extending methods from recent literature. We evaluate the performance of such RL-based ABM agents via experiments on two policy-relevant ABMs: a minority game ABM, and an ABM of Influenza Transmission. We run some analytic experiments on our AI-equipped ABMs e.g. explorations of the effects of behavioral heterogeneity in a population and the emergence of synchronization in a population. The experiments show that RL behavioral models are effective at producing reward-seeking or reward-maximizing behaviors in ABM agents. Furthermore, RL behavioral models can learn to outperform the default adaptive behavioral models in the two ABMs examined.

Parsing natural language to corresponding SQL (NL2SQL) with data driven approaches like deep neural networks attracts much attention in recent years. Existing NL2SQL datasets assume that condition values should appear exactly in natural language questions and the queries are answerable given the table. However, these assumptions may fail in practical scenarios, because user may use different expressions for the same content in the table, and query information outside the table without the full picture of contents in table. Therefore we present TableQA, a large-scale cross-domain Natural Language to SQL dataset in Chinese language consisting 64,891 questions and 20,311 unique SQL queries on over 6,000 tables. Different from exisiting NL2SQL datasets, TableQA requires to generalize well not only to SQL skeletons of different questions and table schemas, but also to the various expressions for condition values. Experiment results show that the state-of-the-art model with 95.1% condition value accuracy on WikiSQL only gets 46.8% condition value accuracy and 43.0% logic form accuracy on TableQA, indicating the proposed dataset is challenging and necessary to handle. Two table-aware approaches are proposed to alleviate the problem, the end-to-end approaches obtains 51.3% and 47.4% accuracy on the condition value and logic form tasks, with improvement of 4.7% and 3.4% respectively.

Standard reinforcement learning (RL) approaches seek to maximize a scalar reward (Sutton and Barto, 1998, 2018; Schulman et al., 2015; Mnih et al., 2015), but in many settings this is insufficient, because the desired properties of the agent behavior are better described using constraints. For example, an autonomous vehicle should not only get to the destination, but should also respect safety, fuel efficiency, and human comfort constraints along the way (Le et al., 2019); a robot should not only fulfill its task, but should also control its wear and tear, for example, by limiting the torque exerted on its motors (Tessler et al., 2019). Moreover, in many settings, we wish to satisfy such constraints already during training and not only during the deployment. For example, a power grid, an autonomous vehicle, or a real robotic hardware should avoid costly failures, where the hardware is damaged or humans are harmed, already during training (Leike et al., 2017; Ray et al., 2020). Constraints are also key in additional sequential decision making applications, such as dynamic pricing with limited supply, e.g., (Besbes and Zeevi, 2009; Babaioff et al., 2015), scheduling of resources on a computer cluster (Mao et al., 2016), and imitation learning, where the goal is to stay close to an expert behavior (Syed and Schapire, 2007; Ziebart et al., 2008; Sun et al., 2019).

Generalization Performance of Deep Learning models trained using Empirical Risk Minimization can be improved significantly by using Data Augmentation strategies such as simple transformations, or using Mixed Samples. We attempt to empirically analyze the impact of such strategies on the transfer of generalization between teacher and student models in a distillation setup. We observe that if a teacher is trained using any of the mixed sample augmentation strategies, such as MixUp or CutMix, the student model distilled from it is impaired in its generalization capabilities. We hypothesize that such strategies limit a model's capability to learn example-specific features, leading to a loss in quality of the supervision signal during distillation. We present a novel Class-Discrimination metric to quantitatively measure this dichotomy in performance and link it to the discriminative capacity induced by the different strategies on a network's latent space.

Simulated annealing-based ontology matching (SANOM) participates for the second time at the ontology alignment evaluation initiative (OAEI) 2019. This paper contains the configuration of SANOM and its results on the anatomy and conference tracks. In comparison to the OAEI 2017, SANOM has improved significantly, and its results are competitive with the state-of-the-art systems. In particular, SANOM has the highest recall rate among the participated systems in the conference track, and is competitive with AML, the best performing system, in terms of F-measure. SANOM is also competitive with LogMap on the anatomy track, which is the best performing system in this track with no usage of particular biomedical background knowledge. SANOM has been adapted to the HOBBIT platfrom and is now available for the registered users.