Members of the SAR11 order Pelagibacterales dominate the surface oceans. Their extensive diversity challenges emerging operational boundaries defined for microbial 'species' and complicates efforts of population genetics to study their evolution. Here, we employed single-amino acid variants (SAAVs) to investigate ecological and evolutionary forces that maintain the genomic heterogeneity within ubiquitous SAR11 populations we accessed through metagenomic read recruitment using a single isolate genome. Integrating amino acid and protein biochemistry with metagenomics revealed that systematic purifying selection against deleterious variants governs non-synonymous variation among very closely related populations of SAR11. SAAVs partitioned metagenomes into two main groups matching large-scale oceanic current temperatures, and six finer proteotypes that connect distant oceanic regions. These findings suggest that environmentally-mediated selection plays a critical role in the journey of cosmopolitan surface ocean microbial populations, and the idea ‘everything is everywhere but the environment selects’ has credence even at the finest resolutions.

In this paper, we propose a novel graph-based approach for semi-supervised learning problems, which considers an adaptive adjacency of the examples throughout the unsupervised portion of the training. Adjacency of the examples is inferred using the predictions of a neural network model which is first initialized by a supervised pretraining. These predictions are then updated according to a novel unsupervised objective which regularizes another adjacency, now linking the output nodes. Regularizing the adjacency of the output nodes, inferred from the predictions of the network, creates an easier optimization problem and ultimately provides that the predictions of the network turn into the optimal embedding. Ultimately, the proposed framework provides an effective and scalable graph-based solution which is natural to the operational mechanism of deep neural networks. Our results show comparable performance with state-of-the-art generative approaches for semi-supervised learning on an easier-to-train, low-cost framework.

Multi-agent reinforcement learning systems aim to provide interacting agents with the ability to collaboratively learn and adapt to the behaviour of other agents. In many real-world applications, the agents can only acquire a partial view of the world. Here we consider a setting whereby most agents' observations are also extremely noisy, hence only weakly correlated to the true state of the environment. Under these circumstances, learning an optimal policy becomes particularly challenging, even in the unrealistic case that an agent's policy can be made conditional upon all other agents' observations. To overcome these difficulties, we propose a multi-agent deep deterministic policy gradient algorithm enhanced by a communication medium (MADDPG-M), which implements a two-level, concurrent learning mechanism. An agent's policy depends on its own private observations as well as those explicitly shared by others through a communication medium. At any given point in time, an agent must decide whether its private observations are sufficiently informative to be shared with others. However, our environments provide no explicit feedback informing an agent whether a communication action is beneficial, rather the communication policies must also be learned through experience concurrently to the main policies. Our experimental results demonstrate that the algorithm performs well in six highly non-stationary environments of progressively higher complexity, and offers substantial performance gains compared to the baselines.

Mastering robotic manipulation skills through reinforcement learning (RL) typically requires the design of shaped reward functions. Recent developments in this area have demonstrated that using sparse rewards, i.e. rewarding the agent only when the task has been successfully completed, can lead to better policies. However, state-action space exploration is more difficult in this case. Recent RL approaches to learning with sparse rewards have leveraged high-quality human demonstrations for the task, but these can be costly, time consuming or even impossible to obtain. In this paper, we propose a novel and effective approach that does not require human demonstrations. We observe that every robotic manipulation task could be seen as involving a locomotion task from the perspective of the object being manipulated, i.e. the object could learn how to reach a target state on its own. In order to exploit this idea, we introduce a framework whereby an object locomotion policy is initially obtained using a realistic physics simulator. This policy is then used to generate auxiliary rewards, called simulated locomotion demonstration rewards (SLDRs), which enable us to learn the robot manipulation policy. The proposed approach has been evaluated on 13 tasks of increasing complexity, and can achieve higher success rate and faster learning rates compared to alternative algorithms. SLDRs are especially beneficial for tasks like multi-object stacking and non-rigid object manipulation.