The exploration mechanism used by a Deep Reinforcement Learning (RL) agent plays a key role in determining its sample efficiency. Thus, improving over random exploration is crucial to solve long-horizon tasks with sparse rewards. We propose to leverage an ensemble of partial solutions as teachers that guide the agent's exploration with action suggestions throughout training. While the setup of learning with teachers has been previously studied, our proposed approach - Actor-Critic with Teacher Ensembles (AC-Teach) - is the first to work with an ensemble of suboptimal teachers that may solve only part of the problem or contradict other each other, forming a unified algorithmic solution that is compatible with a broad range of teacher ensembles. AC-Teach leverages a probabilistic representation of the expected outcome of the teachers' and student's actions to direct exploration, reduce dithering, and adapt to the dynamically changing quality of the learner. We evaluate a variant of AC-Teach that guides the learning of a Bayesian DDPG agent on three tasks - path following, robotic pick and place, and robotic cube sweeping using a hook - and show that it improves largely on sampling efficiency over a set of baselines, both for our target scenario of unconstrained suboptimal teachers and for easier setups with optimal or single teachers. Additional results and videos at https://sites.google.com/view/acteach/home.

Question answering has seen significant advances in recent times, especially with the introduction of increasingly bigger transformer-based models pre-trained on massive amounts of data. While achieving impressive results on many benchmarks, their performances appear to be proportional to the amount of training data available in the target domain. In this work, we explore the ability of current question-answering models to generalize - to both other domains as well as with restricted training data. We find that large amounts of training data are necessary, both for pre-training as well as fine-tuning to a task, for the models to perform well on the designated task. We introduce a novel abductive reasoning approach based on Grenander's Pattern Theory framework to provide self-supervised domain adaptation cues or "pseudo-labels," which can be used instead of expensive human annotations. The proposed self-supervised training regimen allows for effective domain adaptation without losing performance compared to fully supervised baselines. Extensive experiments on two publicly available benchmarks show the efficacy of the proposed approach. We show that neural networks models trained using self-labeled data can retain up to $75\%$ of the performance of models trained on large amounts of human-annotated training data.

Multi-agent reinforcement learning has shown promise on a variety of cooperative tasks as a consequence of recent developments in differentiable inter-agent communication. However, most architectures are limited to pools of homogeneous agents, limiting their applicability. Here we propose a modular framework for learning complex tasks in which a traditional monolithic agent is framed as a collection of cooperating heterogeneous agents. We apply this approach to model sensorimotor coordination in the neocortex as a multi-agent reinforcement learning problem. Our results demonstrate proof-of-concept of the proposed architecture and open new avenues for learning complex tasks and for understanding functional localization in the brain and future intelligent systems.

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games. OpenSpiel supports n-player (single- and multi- agent) zero-sum, cooperative and general-sum, one-shot and sequential, strictly turn-taking and simultaneous-move, perfect and imperfect information games, as well as traditional multiagent environments such as (partially- and fully- observable) grid worlds and social dilemmas. OpenSpiel also includes tools to analyze learning dynamics and other common evaluation metrics. This document serves both as an overview of the code base and an introduction to the terminology, core concepts, and algorithms across the fields of reinforcement learning, computational game theory, and search.

It is becoming increasingly clear that the big tech giants such as Google, Facebook, and Microsoft are extremely generous with their latest machine learning algorithms and packages (they give those away freely) because the entry barrier to the world of algorithms is pretty low right now. The open source community and tools (such as scikit-earn) have come a long way, and plenty of open source initiatives are propelling the vehicles of data science, digital analytics, and machine learning. Standing in 2019, we can safely say that algorithms, programming frameworks, and machine learning packages (or even tutorials and courses how to learn these techniques) are not the scarce resource but high-quality data is. This often becomes a thorny issue on the side of the practitioners in data science (DS) and machine learning (ML) when it comes to tweaking and fine-tuning those algorithms. It will also be wise to point out, at the very beginning, that the current article pertains to the scarcity of data for algorithmic investigation, pedagogical learning, and model prototyping.

Today HPE announced a container-based software solution, HPE ML Ops, to support the entire machine learning model lifecycle for on-premises, public cloud and hybrid cloud environments. The new solution introduces a DevOps-like process to standardize machine learning workflows and accelerate AI deployments from months to days. Only operational machine learning models deliver business value," said Kumar Sreekanti, SVP and CTO, Hybrid IT at HPE. "And with HPE ML Ops, we provide the only enterprise-class solution to operationalize the end-to-end machine learning lifecycle for on-premises and hybrid cloud deployments. The new HPE ML Ops solution extends the capabilities of the BlueData EPIC container software platform, providing data science teams with on-demand access to containerized environments for distributed AI / ML and analytics. BlueData was acquired by HPE in November 2018 to bolster its AI, analytics, and container offerings, and complements HPE's Hybrid IT solutions and HPE Pointnext Services for enterprise AI deployments.

BENGALURU: The Central Board of Secondary Education (CBSE) had earlier announced the introduction of Artificial Intelligence (AI) as an elective for students in classes 9 to 12. The curriculum for the subject is now being developed from scratch by a team from IBM India along with members of its global team and other subject experts. To begin with, IBM will conduct a pilot project in 1,000 schools in Bengaluru, Delhi, Kolkata, Bhubaneswar, Hyderabad and Chennai, before finalising the curriculum and embedding it in the CBSE curriculum from the next academic year. The pilot is being launched in Delhi on Wednesday. The project will start with creating awareness for school principals, followed by a two-and-a half day training of teachers on the foundational skills for the subject.

RV-SKILLS focuses on training and research, with special emphasis on emerging technologies like Artificial Intelligence (AI), Machine Learning (ML), and Automotive Electronics (AE). Limited, RV-SKILLS is set to emerge as the one-stop destination for people pursuing excellence in emerging fields like AI, ML, AE and VLSI design under the tutelage of industry experts. Venkatesh Prasad, Group CEO-RV SKILLS, said, "Technology is advancing at a rapid pace and it is becoming increasingly difficult for people to stay ahead of the learning curve. Today, beyond the realm of engineering education, AI, Analytics, Big Data, ML and AE, are making a big impact on several core sectors. It becomes imperative for us to keep pace with emerging technologies if we have to remain innovative and competitive."

While students may have a career in mind, seldom if ever do they understand the nuances of the path they will need to take to be successful, nor do they have an understanding of the options available to them. On the other hand, academic organizations might lack the input to optimize their programs based on goals, objectives and popular competencies.