Humans, like all animals, both cooperate and compete with each other. Through these interactions we learn to observe, act, and manipulate to maximise our utility function, and continue doing so as others learn with us. This is a decentralised non-stationary learning problem, where to survive and flourish an agent must adapt to the gradual changes of other agents as they learn, as well as capitalise on sudden shifts in their behaviour. To learn in the presence of such non-stationarity, we introduce the Switching Agent Model (SAM) that combines traditional deep reinforcement learning – which typically performs poorly in such settings – with opponent modelling, using uncertainty estimations to robustly switch between multiple policies. We empirically show the success of our approach in a multi-agent continuous-action environment, demonstrating SAM’s ability to identify, track, and adapt to gradual and sudden changes in the behaviour of non-stationary agents.

Policy gradient methods are often applied to reinforcement learning in continuous multiagent games. These methods perform local search in the joint-action space, and as we show, they are susceptable to a game-theoretic pathology known as relative overgeneralization. To resolve this issue, we propose Multiagent Soft Q-learning, which can be seen as the analogue of applying Q-learning to continuous controls. We compare our method to MADDPG, a state-of-the-art approach, and show that our method achieves better coordination in multiagent cooperative tasks, converging to better local optima in the joint action space.

While off-policy temporal difference methods have been broadly used in reinforcement learning due to their efficiency and simple implementation, their Bayesian counterparts have been relatively understudied. This is mainly because the max operator in the Bellman optimality equation brings non-linearity and inconsistent distributions over value function. In this paper, we introduce a new Bayesian approach to off-policy TD methods using Assumed Density Filtering, called ADFQ, which updates beliefs on action-values (Q) through an online Bayesian inference method. Uncertainty measures in the beliefs not only are used in exploration but they provide a natural regularization in the belief updates. We also present a connection between ADFQ and Q-learning. Our empirical results show the proposed ADFQ algorithms outperform comparing algorithms in several task domains. Moreover, our algorithms improve general drawbacks in BRL such as efficiency, usage of uncertainty, and nonlinearity.

Today, the amount of data that can be retrieved from communications networks is extremely high and diverse (e.g., data regarding users behavior, traffic traces, network alarms, signal quality indicators, etc.). Advanced mathematical tools are required to extract useful information from this large set of network data. In particular, Machine Learning (ML) is regarded as a promising methodological area to perform network-data analysis and enable, e.g., automatized network self-configuration and fault management. In this survey we classify and describe relevant studies dealing with the applications of ML to optical communications and networking. Optical networks and system are facing an unprecedented growth in terms of complexity due to the introduction of a huge number of adjustable parameters (such as routing configurations, modulation format, symbol rate, coding schemes, etc.), mainly due to the adoption of, among the others, coherent transmission/reception technology, advanced digital signal processing and to the presence of nonlinear effects in optical fiber systems. Although a good number of research papers have appeared in the last years, the application of ML to optical networks is still in its early stage. In this survey we provide an introductory reference for researchers and practitioners interested in this field. To stimulate further work in this area, we conclude the paper proposing new possible research directions.

We explore Deep Reinforcement Learning in a parameterized action space. Specifically, we investigate how to achieve sample-efficient end-to-end training in these tasks. We propose a new compact architecture for the tasks where the parameter policy is conditioned on the output of the discrete action policy. We also propose two new methods based on the state-of-the-art algorithms Trust Region Policy Optimization (TRPO) and Stochastic Value Gradient (SVG) to train such an architecture. We demonstrate that these methods outperform the state of the art method, Parameterized Action DDPG, on test domains.

Recent advances in the field of inverse reinforcement learning (IRL) have yielded sophisticated frameworks which relax the original modeling assumption that the behavior of an observed agent reflects only a single intention. Instead, the demonstration data is separated into parts to account for the fact that different trajectories may correspond to different intentions, e.g., because they were generated by different domain experts. In this work, we go one step further: using the intuitive concept of subgoals, we build upon the premise that even a single trajectory can be explained more efficiently locally within a certain context than globally, enabling a more compact representation of the observed behavior. Based on this assumption, we build an implicit intentional model of the agent's goals to forecast its behavior in unobserved situations. The result is an integrated Bayesian prediction framework which provides spatially smooth policy estimates that are consistent with the expert's plan and significantly outperform existing IRL solutions. In addition, the framework can be naturally extended to handle scenarios with time-varying expert intentions.

The ability to learn from off-policy data -- data generated from past interaction with the environment -- is essential to data efficient reinforcement learning. Recent work has shown that the use of off-policy data not only allows the re-use of data but can even improve performance in comparison to on-policy reinforcement learning. In this work we investigate if a recently proposed method for learning a better data generation policy, commonly called a behavior policy, can also increase the data efficiency of policy gradient reinforcement learning. Empirical results demonstrate that with an appropriately selected behavior policy we can estimate the policy gradient more accurately. The results also motivate further work into developing methods for adapting the behavior policy as the policy we are learning changes.

Sponsored search is an indispensable business model and a major revenue contributor of almost all the search engines. From the advertisers' side, participating in ranking the search results by paying for the sponsored search advertisement to attract more awareness and purchase facilitates their commercial goal. From the users' side, presenting personalized advertisement reflecting their propensity would make their online search experience more satisfactory. Sponsored search platforms rank the advertisements by a ranking function to determine the list of advertisements to show and the charging price for the advertisers. Hence, it is crucial to find a good ranking function which can simultaneously satisfy the platform, the users and the advertisers. Moreover, advertisements showing positions under different queries from different users may associate with advertisement candidates of different bid price distributions and click probability distributions, which requires the ranking functions to be optimized adaptively to the traffic characteristics. In this work, we proposed a generic framework to optimize the ranking functions by deep reinforcement learning methods. The framework is composed of two parts: an offline learning part which initializes the ranking functions by learning from a simulated advertising environment, allowing adequate exploration of the ranking function parameter space without hurting the performance of the commercial platform. An online learning part which further optimizes the ranking functions by adapting to the online data distribution. Experimental results on a large-scale sponsored search platform confirm the effectiveness of the proposed method.

Data efficiency, i.e., learning from small data sets, is critical in many practical applications where data collection is time consuming or expensive, e.g., robotics, animal experiments or drug design. Meta learning is one way to increase the data efficiency of learning algorithms by generalizing learned concepts from a set of training tasks to unseen, but related, tasks. Often, this relationship between tasks is hard coded or relies in some other way on human expertise. In this paper, we propose to automatically learn the relationship between tasks using a latent variable model. Our approach finds a variational posterior over tasks and averages over all plausible (according to this posterior) tasks when making predictions. We apply this framework within a model-based reinforcement learning setting for learning dynamics models and controllers of many related tasks. We apply our framework in a model-based reinforcement learning setting, and show that our model effectively generalizes to novel tasks, and that it reduces the average interaction time needed to solve tasks by up to 60% compared to strong baselines.

Existing research studies on vision and language grounding for robot navigation focus on improving model-free deep reinforcement learning (DRL) models in synthetic environments. However, model-free DRL models do not consider the dynamics in the real-world environments, and they often fail to generalize to new scenes. In this paper, we take a radical approach to bridge the gap between synthetic studies and real-world practices---We propose a novel, planned-ahead hybrid reinforcement learning model that combines model-free and model-based reinforcement learning to solve a real-world vision-language navigation task. Our look-ahead module tightly integrates a look-ahead policy model with an environment model that predicts the next state and the reward. Experimental results suggest that our proposed method significantly outperforms the baselines and achieves the best on the real-world Room-to-Room dataset. Moreover, our scalable method is more generalizable when transferring to unseen environments, and the relative success rate is increased by 15.5% on the unseen test set.