Nowadays, live video streaming events have become a mainstay in viewer's communication in large international enterprises. Provided that viewers are distributed worldwide, the main challenge resides on how to schedule the optimal event's time so as to improve both the viewer's engagement and adoption. In this paper we present a multi-task deep reinforcement learning model to select the time of a live video streaming event, aiming to optimize the viewer's engagement and adoption at the same time. We consider the engagement and adoption of the viewers as independent tasks and formulate a unified loss function to learn a common policy. In addition, we account for the fact that each task might have different contribution to the training strategy of the agent. Therefore, to determine the contribution of each task to the agent's training, we design a Transformer's architecture for the state-action transitions of each task. We evaluate our proposed model on four real-world datasets, generated by the live video streaming events of four large enterprises spanning from January 2019 until March 2021. Our experiments demonstrate the effectiveness of the proposed model when compared with several state-of-the-art strategies. For reproduction purposes, our evaluation datasets and implementation are publicly available at https://github.com/stefanosantaris/merlin.

This paper addresses the problem of policy selection in domains with abundant logged data, but with a very restricted interaction budget. Solving this problem would enable safe evaluation and deployment of offline reinforcement learning policies in industry, robotics, and healthcare domain among others. Several off-policy evaluation (OPE) techniques have been proposed to assess the value of policies using only logged data. However, there is still a big gap between the evaluation by OPE and the full online evaluation in the real environment. To reduce this gap, we introduce a novel \emph{active offline policy selection} problem formulation, which combined logged data and limited online interactions to identify the best policy. We rely on the advances in OPE to warm start the evaluation. We build upon Bayesian optimization to iteratively decide which policies to evaluate in order to utilize the limited environment interactions wisely. Many candidate policies could be proposed, thus, we focus on making our approach scalable and introduce a kernel function to model similarity between policies. We use several benchmark environments to show that the proposed approach improves upon state-of-the-art OPE estimates and fully online policy evaluation with limited budget. Additionally, we show that each component of the proposed method is important, it works well with various number and quality of OPE estimates and even with a large number of candidate policies.

Social learning, copying other's behavior without actual experience, offers a cost-effective means of knowledge acquisition. However, it raises the fundamental question of which individuals have reliable information: successful individuals versus the majority. The former and the latter are known respectively as success-based and conformist social learning strategies. We show here that while the success-based strategy fully exploits the benign environment of low uncertainly, it fails in uncertain environments. On the other hand, the conformist strategy can effectively mitigate this adverse effect. Based on these findings, we hypothesized that meta-control of individual and social learning strategies provides effective and sample-efficient learning in volatile and uncertain environments. Simulations on a set of environments with various levels of volatility and uncertainty confirmed our hypothesis. The results imply that meta-control of social learning affords agents the leverage to resolve environmental uncertainty with minimal exploration cost, by exploiting others' learning as an external knowledge base.

Batch reinforcement learning (RL) broadly refers to the problem of finding a policy with high expected return in a stochastic control problem when only a batch of data collected from the controlled system is available. Here, we consider this problem for finite state-action ("tabular") Markov decision processes (MDPs) when the data takes the form of trajectories obtained by following some logging policy. In more details, the trajectories are composed of sequences of states, actions, and rewards, where the action is chosen by the logging policy and the next state and rewards follow the distributions specified by the MDP's transition parameters. Arguably, this is the most natural problem setting to consider in batch learning. The basic questions are (a) what logging policy should one choose to generate the data so as to maximize the chance of obtaining a good policy with as little data as possible; and (b) how many transitions are sufficient and necessary to obtain a good policy and which algorithm to use to obtain such a policy? Note that here the logging policy needs to be chosen a priori, that is, before the data collection process begins. An alternative way of saying this is that the data collection is done in a passive way. Our main results are as follows: First, we show that (perhaps unsurprisingly), in the lack of extra information about the nature of the MDP, the best logging policy should choose actions uniformly at random. Next, we show that the number of transitions necessary and sufficient to obtain a good policy, the sample complexity of learning, is an exponential function of the minimum of the number of states and the planning horizon.

In a paper published in the peer-reviewed scientific journal Nature last week, scientists at Google Brain introduced a deep reinforcement learning technique for floorplanning, the process of arranging the placement of different components of computer chips. The researchers managed to use the reinforcement learning technique to design the next generation of Tensor Processing Units, Google's specialized artificial intelligence processors. The use of software in chip design is not new. But according to the Google researchers, the new reinforcement learning model "automatically generates chip floorplans that are superior or comparable to those produced by humans in all key metrics, including power consumption, performance and chip area." And it does it in a fraction of the time it would take a human to do so. The AI's superiority to human performance has drawn a lot of attention.

Simulation has recently become key for deep reinforcement learning to safely and efficiently acquire general and complex control policies from visual and proprioceptive inputs. Tactile information is not usually considered despite its direct relation to environment interaction. In this work, we present a suite of simulated environments tailored towards tactile robotics and reinforcement learning. A simple and fast method of simulating optical tactile sensors is provided, where high-resolution contact geometry is represented as depth images. Proximal Policy Optimisation (PPO) is used to learn successful policies across all considered tasks.

This article is part of "the philosophy of artificial intelligence," a series of posts that explore the ethical, moral, and social implications of AI today and in the future Last week, I wrote an analysis of "Reward Is Enough," a paper by scientists at DeepMind. As the title suggests, the researchers hypothesize that the right reward is all you need to create the abilities associated with intelligence, such as perception, motor functions, and language. This is in contrast with AI systems that try to replicate specific functions of natural intelligence such as classifying images, navigating physical environments, or completing sentences. The researchers go as far as suggesting that with well-defined reward, a complex environment, and the right reinforcement learning algorithm, we will be able to reach artificial general intelligence, the kind of problem-solving and cognitive abilities found in humans and, to a lesser degree, in animals. The article and the paper triggered a heated debate on social media, with reactions going from full support of the idea to outright rejection. Of course, both sides make valid claims.

Recent renewed interest in multi-agent reinforcement learning (MARL) has generated an impressive array of techniques that leverage deep reinforcement learning, primarily actor-critic architectures, and can be applied to a limited range of settings in terms of observability and communication. However, a continuing limitation of much of this work is the curse of dimensionality when it comes to representations based on joint actions, which grow exponentially with the number of agents. In this paper, we squarely focus on this challenge of scalability. We apply the key insight of action anonymity, which leads to permutation invariance of joint actions, to two recently presented deep MARL algorithms, MADDPG and IA2C, and compare these instantiations to another recent technique that leverages action anonymity, viz., mean-field MARL. We show that our instantiations can learn the optimal behavior in a broader class of agent networks than the mean-field method, using a recently introduced pragmatic domain.

Purpose: Image classification is perhaps the most fundamental task in imaging AI. However, labeling images is time-consuming and tedious. We have recently demonstrated that reinforcement learning (RL) can classify 2D slices of MRI brain images with high accuracy. Here we make two important steps toward speeding image classification: Firstly, we automatically extract class labels from the clinical reports. Secondly, we extend our prior 2D classification work to fully 3D image volumes from our institution. Hence, we proceed as follows: in Part 1, we extract labels from reports automatically using the SBERT natural language processing approach. Then, in Part 2, we use these labels with RL to train a classification Deep-Q Network (DQN) for 3D image volumes. Methods: For Part 1, we trained SBERT with 90 radiology report impressions. We then used the trained SBERT to predict class labels for use in Part 2. In Part 2, we applied multi-step image classification to allow for combined Deep-Q learning using 3D convolutions and TD(0) Q learning. We trained on a set of 90 images. We tested on a separate set of 61 images, again using the classes predicted from patient reports by the trained SBERT in Part 1. For comparison, we also trained and tested a supervised deep learning classification network on the same set of training and testing images using the same labels. Results: Part 1: Upon training with the corpus of radiology reports, the SBERT model had 100% accuracy for both normal and metastasis-containing scans. Part 2: Then, using these labels, whereas the supervised approach quickly overfit the training data and as expected performed poorly on the testing set (66% accuracy, just over random guessing), the reinforcement learning approach achieved an accuracy of 92%. The results were found to be statistically significant, with a p-value of 3.1 x 10^-5.

The performance of a reinforcement learning (RL) system depends on the computational architecture used to approximate a value function. Deep learning methods provide both optimization techniques and architectures for approximating nonlinear functions from noisy, high-dimensional observations. However, prevailing optimization techniques are not designed for strictly-incremental online updates. Nor are standard architectures designed for observations with an a priori unknown structure: for example, light sensors randomly dispersed in space. This paper proposes an online RL prediction algorithm with an adaptive architecture that efficiently finds useful nonlinear features. The algorithm is evaluated in a spatial domain with high-dimensional, stochastic observations. The algorithm outperforms non-adaptive baseline architectures and approaches the performance of an architecture given side-channel information. These results are a step towards scalable RL algorithms for more general problems, where the observation structure is not available.