We consider stochastic optimization problems where data is drawn from a Markov chain. Existing methods for this setting crucially rely on knowing the mixing time of the chain, which in real-world applications is usually unknown. We propose the first optimization method that does not require the knowledge of the mixing time, yet obtains the optimal asymptotic convergence rate when applied to convex problems. We further show that our approach can be extended to: (i) finding stationary points in non-convex optimization with Markovian data, and (ii) obtaining better dependence on the mixing time in temporal difference (TD) learning; in both cases, our method is completely oblivious to the mixing time. Our method relies on a novel combination of multi-level Monte Carlo (MLMC) gradient estimation together with an adaptive learning method.

In recent years, symbolic regression has been of wide interest to provide an interpretable symbolic representation of potentially large data relationships. Initially circled to genetic algorithms, symbolic regression methods now include a variety of Deep Learning based alternatives. However, these methods still do not generalize well to real-world data, mainly because they hardly include domain knowledge nor consider physical relationships between variables such as known equations and units. Regarding these issues, we propose a Reinforcement-Based Grammar-Guided Symbolic Regression (RBG2-SR) method that constrains the representational space with domain-knowledge using context-free grammar as reinforcement action space. We detail a Partially-Observable Markov Decision Process (POMDP) modeling of the problem and benchmark our approach against state-of-the-art methods. We also analyze the POMDP state definition and propose a physical equation search use case on which we compare our approach to grammar-based and non-grammarbased symbolic regression methods. The experiment results show that our method is competitive against other state-of-the-art methods on the benchmarks and offers the best error-complexity trade-off, highlighting the interest of using a grammar-based method in a real-world scenario.

This paper presents a proof-of-concept implementation of the AI-as-a-Service toolkit developed within the H2020 TEACHING project and designed to implement an autonomous driving personalization system according to the output of an automatic driver's stress recognition algorithm, both of them realizing a Cyber-Physical System of Systems. In addition, we implemented a data-gathering subsystem to collect data from different sensors, i.e., wearables and cameras, to automatize stress recognition. The system was attached for testing to a driving simulation software, CARLA, which allows testing the approach's feasibility with minimum cost and without putting at risk drivers and passengers. At the core of the relative subsystems, different learning algorithms were implemented using Deep Neural Networks, Recurrent Neural Networks, and Reinforcement Learning.

Created by Lazy Programmer Inc. English [Auto-generated] Created by Lazy Programmer Inc. This is technically Deep Learning in Python part 11 of my deep learning series, and my 3rd reinforcement learning course. Deep Reinforcement Learning is actually the combination of 2 topics: Reinforcement Learning and Deep Learning (Neural Networks). While both of these have been around for quite some time, it's only been recently that Deep Learning has really taken off, and along with it, Reinforcement Learning. The maturation of deep learning has propelled advances in reinforcement learning, which has been around since the 1980s, although some aspects of it, such as the Bellman equation, have been for much longer.

This paper introduces a novel approach for abstraction selection in reinforcement learning problems modelled as factored Markov decision processes (MDPs), for which a state is described via a set of state components. In abstraction selection, an agent must choose an abstraction from a set of candidate abstractions, each build up from a different combination of state components.

Reinforcement Learning is beginning to be applied outside traditional domains such as robotics, and into human-centric domains such as healthcare and education. In these domains, two problems are critical to address: We must be able to evaluate algorithms with a collection of prior data if one is available, and we must devise algorithms that carefully trade off exploration and exploitation in such a way that they are guaranteed to converge to optimal behavior quickly, while retaining very good performance with limited data. In this thesis, I examine these two problems, with an eye towards applications to educational games.

Reinforcement learning algorithms typically require too many trial-and-error' experiences before reaching a desirable behaviour. A considerable amount of ongoing research is focused on speeding up this learning process by using external knowledge. We contribute in several ways, proposing novel approaches to transfer learning and learning from demonstration, as well as an ensemble approach to combine knowledge from various sources.

In this extended abstract we introduce the Arcade Learning Environment (ALE): both a challenge problem and a platform and methodology for evaluating the development of general, domain-independent AI technology. ALE provides an interface to hundreds of Atari 2600 game environments, each one different, interesting, and designed to be a challenge for human players. ALE presents significant research challenges for reinforcement learning, model learning, model-based planning, imitation learning, transfer learning, and intrinsic motivation. Most importantly, it provides a rigorous testbed for evaluating and comparing approaches to these problems. We illustrate the promise of ALE by presenting a benchmark set of domain-independent agents designed using well-established AI techniques for both reinforcement learning and planning. In doing so, we also propose an evaluation methodology made possible by ALE, reporting empirical results on over 55 different games. We conclude with a brief update on the latest ALE developments. All of the software, including the benchmark agents, is publicly available.

Exploration strategy is an essential part of learning agents in model-based Reinforcement Learning. R-MAX and V-MAX are PAC-MDP strategies proved to have polynomial sample complexity; yet, their exploration behavior tend to be overly cautious in practice. We propose the principle of Increasingly Cautious Optimism (ICO) to automatically cut off unnecessarily cautious exploration, and apply ICO to R-MAX and V-MAX, yielding two new strategies, namely Increasingly Cautious R-MAX (ICR) and Increasingly Cautious V-MAX (ICV). We prove that both ICR and ICV are PACMDP, and show that their improvement is guaranteed by a tighter sample complexity upper bound. Then, we demonstrate their significantly improved performance through empirical results.

In this work, we introduce the first approach to the Inverse Reinforcement Learning (IRL) problem in relational domains. IRL has been used to recover a more compact representation of the expert policy leading to better generalization performances among different contexts. On the other hand, relational learning allows representing problems with a varying number of objects (potentially infinite), thus provides more generalizable representations of problems and skills. We show how these different formalisms allow one to create a new IRL algorithm for relational domains that can recover with great efficiency rewards from expert data that have strong generalization and transfer properties. We evaluate our algorithm in representative tasks and study the impact of diverse experimental conditions such as: the number of demonstrations, knowledge about the dynamics, transfer among varying dimensions of a problem, and changing dynamics.