Providing reinforcement learning agents with informationally rich human knowledge can dramatically improve various aspects of learning. Prior work has developed different kinds of shaping methods that enable agents to learn efficiently in complex environments. All these methods, however, tailor human guidance to agents in specialized shaping procedures, thus embodying various characteristics and advantages in different domains. In this paper, we investigate the interplay between different shaping methods for more robust learning performance. We propose an adaptive shaping algorithm which is capable of learning the most suitable shaping method in an on-line manner. Results in two classic domains verify its effectiveness from both simulated and real human studies, shedding some light on the role and impact of human factors in human-robot collaborative learning.

We propose DecaProp (Densely Connected Attention Propagation), a new densely connected neural architecture for reading comprehension (RC). There are two distinct characteristics of our model. Firstly, our model densely connects all pairwise layers of the network, modeling relationships between passage and query across all hierarchical levels. Secondly, the dense connectors in our network are learned via attention instead of standard residual skip-connectors. To this end, we propose novel Bidirectional Attention Connectors (BAC) for efficiently forging connections throughout the network. We conduct extensive experiments on four challenging RC benchmarks. Our proposed approach achieves state-of-the-art results on all four, outperforming existing baselines by up to $2.6\%-14.2\%$ in absolute F1 score.

Some of China's smartest high school graduates have been recruited to study the manufacturing of AI weaponry to keep Beijing ahead of the war game. The Chinese teenagers are studying at Beijing Institute of Technology, a top university in the country specialising in engineering and national defence. The class, unveiled last month, comprises 31 students who are selected based on their academic achievements and their level of patriotism, according the school. AI weapons, called by some as'killer robots', generally mean automated weapons which select, engage and eliminate human targets without the involvement of other humans. It has been described as the third revolution in warfare - after gunpowder and nuclear arms - and has been a controversial topic due to the ethics behind them.

Traditional learning methods for training Markov random fields require doing inference over all variables to compute the likelihood gradient. The iteration complexity for those methods therefore scales with the size of the graphical models. In this paper, we propose \emph{block belief propagation learning} (BBPL), which uses block-coordinate updates of approximate marginals to compute approximate gradients, removing the need to compute inference on the entire graphical model. Thus, the iteration complexity of BBPL does not scale with the size of the graphs. We prove that the method converges to the same solution as that obtained by using full inference per iteration, despite these approximations, and we empirically demonstrate its scalability improvements over standard training methods.

In recent years, distance education has enjoyed a major boom. Much work at The Open University (OU) has focused on improving retention rates in these modules by providing timely support to students who are at risk of failing the module. In this paper we explore methods for analysing student activity in online virtual learning environment (VLE) -- General Unary Hypotheses Automaton (GUHA) and Markov chain-based analysis -- and we explain how this analysis can be relevant for module tutors and other student support staff. We show that both methods are a valid approach to modelling student activities. An advantage of the Markov chain-based approach is in its graphical output and in the possibility to model time dependencies of the student activities.

Executing natural language navigation instructions from raw observations requires solving language, perception, planning, and control problems. Consider instructing a quadcopter drone using natural language. Figure 1 shows an example instruction. Resolving the instruction requires identifying the blue fence, anvil and tree in the world, understanding the spatial constraints towards and on the right, planning a trajectory that satisfies these constraints, and continuously controlling the quadcopter to follow the trajectory. Existing work has addressed this problem mostly using manually-designed symbolic representations for language meaning and environment [1, 2, 3, 4, 5, 6].

Achieving coordination is crucial in organizational control. This paper investigates a middle ground solution between decentralized interactions and centralized administrations for coordinating agents beyond inefficient behavior. We first propose the price of governance (PoG) to evaluate how such a middle ground solution performs in terms of effectiveness and cost. We then propose a hierarchical supervision framework to explicitly model the PoG, and define step by step how to realize the core principle of the framework and compute the optimal PoG for a control problem. Two illustrative case studies are carried out to exemplify the applications of the proposed framework and its methodology. Results show that by properly formulating and implementing each step, the hierarchical supervision framework is capable of promoting coordination among agents while bounding administrative cost to a minimum in different kinds of organizational control problems.

A group of some of China's smartest students have been recruited straight from high school to begin training as the world's youngest AI weapons scientists. Local media reports: The 27 boys and four girls, all aged 18 and under, were selected for the four-year "experimental programme for intelligent weapons systems" at the Beijing Institute of Technology (BIT) from more than 5,000 candidates, the school said on its website. The BIT is one of the country's top weapons research institutes, and the launch of the new programme is evidence of the weight it places on the development of AI technology for military use. China is in competition with the United States and other nations in the race to develop deadly AI applications -- from nuclear submarines with self-learning chips to microscopic robots that can crawl into human blood vessels.

What is the best way to define algorithmic fairness? There has been much recent debate on algorithmic fairness. While many definitions of fairness have been proposed in the computer science literature, there is no clear agreement over a particular definition. In this work, we investigate ordinary people's perceptions of three of these fairness definitions. Across two online experiments, we test which definitions people perceive to be the fairest in the context of loan decisions, and whether those fairness perceptions change with the addition of sensitive information (i.e., race of the loan applicants). We find a clear preference for one definition, and the general results seem to align with the principle of affirmative action.

Abstract-- Multi-objective reinforcement learning (MORL) is the generalization of standard reinforcement learning (RL) approaches to solve sequential decision making problems that consist of several, possibly conflicting, objectives. Generally, in such formulations, there is no single optimal policy which optimizes all the objectives simultaneously, and instead, a number of policies has to be found, each optimizing a preference of the objectives. In this paper, we introduce a novel MORL approach by training a meta-policy, a policy simultaneously trained with multiple tasks sampled from a task distribution, for a number of randomly sampled Markov decision processes (MDPs). In other words, the MORL is framed as a meta-learning problem, with the task distribution given by a distribution over the preferences. We demonstrate that such a formulation results in a better approximation of the Pareto optimal solutions, in terms of both the optimality and the computational efficiency. We evaluated our method on obtaining Pareto optimal policies using a number of continuous control problems with high degrees of freedom. I. INTRODUCTION Reinforcement learning (RL) is a framework to train an agent to acquire a behavior by reinforcing actions that maximize a notion of task-relevant future rewards. A reward function, i.e., the function that assigns a reward value to every action-decision made by the agent, is designed to guide the training to implement the behavior.