Recent research has turned to Reinforcement Learning (RL) to solve challenging decision problems, as an alternative to hand-tuned heuristics. RL can learn good policies without the need for modeling the environment's dynamics. Despite this promise, RL remains an impractical solution for many real-world systems problems. A particularly challenging case occurs when the environment changes over time, i.e. it exhibits non-stationarity. In this work, we characterize the challenges introduced by non-stationarity and develop a framework for addressing them to train RL agents in live systems. Such agents must explore and learn new environments, without hurting the system's performance, and remember them over time. To this end, our framework (1) identifies different environments encountered by the live system, (2) explores and trains a separate expert policy for each environment, and (3) employs safeguards to protect the system's performance. We apply our framework to two systems problems: straggler mitigation and adaptive video streaming, and evaluate it against a variety of alternative approaches using real-world and synthetic data. We show that each component of our framework is necessary to cope with non-stationarity.

Reinforcement Learning and recently Deep Reinforcement Learning are popular methods for solving sequential decision making problems modeled as Markov Decision Processes. RL modeling of a problem and selecting algorithms and hyper-parameters require careful considerations as different configurations may entail completely different performances. These considerations are mainly the task of RL experts; however, RL is progressively becoming popular in other fields where the researchers and system designers are not RL experts. Besides, many modeling decisions, such as defining state and action space, size of batches and frequency of batch updating, and number of timesteps are typically made manually. For these reasons, automating different components of RL framework is of great importance and it has attracted much attention in recent years. Automated RL provides a framework in which different components of RL including MDP modeling, algorithm selection and hyper-parameter optimization are modeled and defined automatically. In this article, we explore the literature and present recent work that can be used in automated RL. Moreover, we discuss the challenges, open questions and research directions in AutoRL.

The goal of this paper is to investigate a control theoretic analysis of linear stochastic iterative algorithm and temporal difference (TD) learning. TD-learning is a linear stochastic iterative algorithm to estimate the value function of a given policy for a Markov decision process, which is one of the most popular and fundamental reinforcement learning algorithms. While there has been a series of successful works in theoretical analysis of TD-learning, it was not until recently that researchers found some guarantees on its statistical efficiency. In this paper, we propose a control theoretic finite-time analysis TD-learning, which exploits standard notions in linear system control communities. Therefore, the proposed work provides additional insights on TD-learning and reinforcement learning with simple concepts and analysis tools in control theory.

A common approach to prediction and planning in partially observable domains is to use recurrent neural networks (RNNs), which ideally develop and maintain a latent memory about hidden, task-relevant factors. We hypothesize that many of these hidden factors in the physical world are constant over time, changing only sparsely. To study this hypothesis, we propose Gated $L_0$ Regularized Dynamics (GateL0RD), a novel recurrent architecture that incorporates the inductive bias to maintain stable, sparsely changing latent states. The bias is implemented by means of a novel internal gating function and a penalty on the $L_0$ norm of latent state changes. We demonstrate that GateL0RD can compete with or outperform state-of-the-art RNNs in a variety of partially observable prediction and control tasks. GateL0RD tends to encode the underlying generative factors of the environment, ignores spurious temporal dependencies, and generalizes better, improving sampling efficiency and overall performance in model-based planning and reinforcement learning tasks. Moreover, we show that the developing latent states can be easily interpreted, which is a step towards better explainability in RNNs.

Finding low dimensional representation of data from long-timescale trajectories of biomolecular processes such as protein-folding or ligand-receptor binding is of fundamental importance and kinetic models such as Markov modeling have proven useful in describing the kinetics of these systems. Recently, an unsupervised machine learning technique called VAMPNet was introduced to learn the low dimensional representation and linear dynamical model in an end-to-end manner. VAMPNet is based on variational approach to Markov processes (VAMP) and relies on neural networks to learn the coarse-grained dynamics. In this contribution, we combine VAMPNet and graph neural networks to generate an end-to-end framework to efficiently learn high-level dynamics and metastable states from the long-timescale molecular dynamics trajectories. This method bears the advantages of graph representation learning and uses graph message passing operations to generate an embedding for each datapoint which is used in the VAMPNet to generate a coarse-grained representation. This type of molecular representation results in a higher resolution and more interpretable Markov model than the standard VAMPNet enabling a more detailed kinetic study of the biomolecular processes. Our GraphVAMPNet approach is also enhanced with an attention mechanism to find the important residues for classification into different metastable states.

We introduce PyHHMM, an object-oriented open-source Python implementation of Heterogeneous-Hidden Markov Models (HHMMs). In addition to HMM's basic core functionalities, such as different initialization algorithms and classical observations models, i.e., continuous and multinoulli, PyHHMM distinctively emphasizes features not supported in similar available frameworks: a heterogeneous observation model, missing data inference, different model order selection criterias, and semi-supervised training. These characteristics result in a feature-rich implementation for researchers working with sequential data. PyHHMM relies on the numpy, scipy, scikit-learn, and seaborn Python packages, and is distributed under the Apache-2.0 License. PyHHMM's source code is publicly available on Github (https://github.com/fmorenopino/HeterogeneousHMM) to facilitate adoptions and future contributions. A detailed documentation (https://pyhhmm.readthedocs.io/en/latest), which covers examples of use and models' theoretical explanation, is available. The package can be installed through the Python Package Index (PyPI), via 'pip install pyhhmm'.

Partially Observable Markov Decision Processes (POMDPs) are a natural and general model in reinforcement learning that take into account the agent's uncertainty about its current state. In the literature on POMDPs, it is customary to assume access to a planning oracle that computes an optimal policy when the parameters are known, even though the problem is known to be computationally hard. Almost all existing planning algorithms either run in exponential time, lack provable performance guarantees, or require placing strong assumptions on the transition dynamics under every possible policy. In this work, we revisit the planning problem and ask: are there natural and well-motivated assumptions that make planning easy? Our main result is a quasipolynomial-time algorithm for planning in (one-step) observable POMDPs. Specifically, we assume that well-separated distributions on states lead to well-separated distributions on observations, and thus the observations are at least somewhat informative in each step. Crucially, this assumption places no restrictions on the transition dynamics of the POMDP; nevertheless, it implies that near-optimal policies admit quasi-succinct descriptions, which is not true in general (under standard hardness assumptions). Our analysis is based on new quantitative bounds for filter stability -- i.e. the rate at which an optimal filter for the latent state forgets its initialization. Furthermore, we prove matching hardness for planning in observable POMDPs under the Exponential Time Hypothesis.

Critical periods are phases during which a toddler's brain develops in spurts. To promote children's cognitive development, proper guidance is critical in this stage. However, it is not clear whether such a critical period also exists for the training of AI agents. Similar to human toddlers, well-timed guidance and multimodal interactions might significantly enhance the training efficiency of AI agents as well. To validate this hypothesis, we adapt this notion of critical periods to learning in AI agents and investigate the critical period in the virtual environment for AI agents. We formalize the critical period and Toddler-guidance learning in the reinforcement learning (RL) framework. Then, we built up a toddler-like environment with VECA toolkit to mimic human toddlers' learning characteristics. We study three discrete levels of mutual interaction: weak-mentor guidance (sparse reward), moderate mentor guidance (helper-reward), and mentor demonstration (behavioral cloning). We also introduce the EAVE dataset consisting of 30,000 real-world images to fully reflect the toddler's viewpoint. We evaluate the impact of critical periods on AI agents from two perspectives: how and when they are guided best in both uni- and multimodal learning. Our experimental results show that both uni- and multimodal agents with moderate mentor guidance and critical period on 1 million and 2 million training steps show a noticeable improvement. We validate these results with transfer learning on the EAVE dataset and find the performance advancement on the same critical period and the guidance.

This is Part II of the two-part comprehensive survey devoted to a computing framework most commonly known under the names Hyperdimensional Computing and Vector Symbolic Architectures (HDC/VSA). Both names refer to a family of computational models that use high-dimensional distributed representations and rely on the algebraic properties of their key operations to incorporate the advantages of structured symbolic representations and vector distributed representations. Holographic Reduced Representations is an influential HDC/VSA model that is well-known in the machine learning domain and often used to refer to the whole family. However, for the sake of consistency, we use HDC/VSA to refer to the area. Part I of this survey covered foundational aspects of the area, such as historical context leading to the development of HDC/VSA, key elements of any HDC/VSA model, known HDC/VSA models, and transforming input data of various types into high-dimensional vectors suitable for HDC/VSA. This second part surveys existing applications, the role of HDC/VSA in cognitive computing and architectures, as well as directions for future work. Most of the applications lie within the machine learning/artificial intelligence domain, however we also cover other applications to provide a thorough picture. The survey is written to be useful for both newcomers and practitioners.

Active inference is an account of cognition and behavior in complex systems which brings together action, perception, and learning under the theoretical mantle of Bayesian inference. Active inference has seen growing applications in academic research, especially in fields that seek to model human or animal behavior. While in recent years, some of the code arising from the active inference literature has been written in open source languages like Python and Julia, to-date, the most popular software for simulating active inference agents is the DEM toolbox of SPM, a MATLAB library originally developed for the statistical analysis and modelling of neuroimaging data. Increasing interest in active inference, manifested both in terms of sheer number as well as diversifying applications across scientific disciplines, has thus created a need for generic, widely-available, and user-friendly code for simulating active inference in open-source scientific computing languages like Python. The Python package we present here, pymdp (see https://github.com/infer-actively/pymdp), represents a significant step in this direction: namely, we provide the first open-source package for simulating active inference with partially-observable Markov Decision Processes or POMDPs. We review the package's structure and explain its advantages like modular design and customizability, while providing in-text code blocks along the way to demonstrate how it can be used to build and run active inference processes with ease. We developed pymdp to increase the accessibility and exposure of the active inference framework to researchers, engineers, and developers with diverse disciplinary backgrounds. In the spirit of open-source software, we also hope that it spurs new innovation, development, and collaboration in the growing active inference community.