Being Optimistic to Be Conservative: Quickly Learning a CV aR Policy Ramtin Keramati 1, Christoph Dann 2, Alex T amkin 3, Emma Brunskill 3 1 Institute of Computational and Mathematical Engineering (ICME), Stanford University, California, USA 2 Machine Learning Department, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA 3 Department of Computer Science, Stanford University, California, USA {keramati,atamkin,ebrun } @cs.stanford.edu Abstract While maximizing expected return is the goal in most reinforcement learning approaches, risk-sensitive objectives such as conditional value at risk (CV aR) are more suitable for many high-stakes applications. However, relatively little is known about how to explore to quickly learn policies with good CV aR. In this paper, we present the first algorithm for sample-efficient learning of CV aR-optimal policies in Markov decision processes based on the optimism in the face of uncertainty principle. This method relies on a novel optimistic version of the distributional Bellman operator that moves probability mass from the lower to the upper tail of the return distribution. We prove asymptotic convergence and optimism of this operator for the tabular policy evaluation case. We further demonstrate that our algorithm finds CV aR-optimal policies substantially faster than existing baselines in several simulated environments with discrete and continuous state spaces. Introduction A key goal in reinforcement learning (RL) is to quickly learn to make good decisions by interacting with an environment. In most cases the quality of the decision policy is evaluated with respect to its expected (discounted) sum of rewards. However, in many interesting cases, it is important to consider the full distributions over the potential sum of rewards, and the desired objective may be a risk-sensitive measure of this distribution. For example, a patient undergoing a surgery for a knee replacement will (hopefully) only experience that procedure once or twice, and may will be interested in the distribution of potential results for a single procedure, rather than what may happen on average if he or she were to undertake that procedure hundreds of time. Finance and (machine) control are other cases where interest in risk-sensitive outcomes are common. A popular risk-sensitive measure of a distribution of outcomes is the Conditional V alue at Risk (CV aR) (Artzner et al. 1999). Intuitively, CV aR is the expected reward in the worst α -fraction of outcomes, and has seen extensive use in financial portfolio optimization (Zhu and Fukushima 2009), often under the name "expected shortfall".

Machine learning algorithms are extensively used to make increasingly more consequential decisions, so that achieving optimal predictive performance can no longer be the only focus. This paper explores intersectional fairness, that is fairness when intersections of multiple sensitive attributes -- such as race, age, nationality, etc. -- are considered. Previous research has mainly been focusing on fairness with respect to a single sensitive attribute, with intersectional fairness being comparatively less studied despite its critical importance for modern machine learning applications. We introduce intersectional fairness metrics by extending prior work, and provide different methodologies to audit discrimination in a given dataset or model outputs. Secondly, we develop novel post-processing techniques to mitigate any detected bias in a classification model. Our proposed methodology does not rely on any assumptions regarding the underlying model and aims at guaranteeing fairness while preserving good predictive performance. Finally, we give guidance on a practical implementation, showing how the proposed methods perform on a real-world dataset.

For other useful tutorials, follow this link, or check my blogs.

Monte Carlo methods are a class of techniques for randomly sampling a probability distribution. There are many problem domains where describing or estimating the probability distribution is relatively straightforward, but calculating a desired quantity is intractable. This may be due to many reasons, such as the stochastic nature of the domain or an exponential number of random variables. Instead, a desired quantity can be approximated by using random sampling, referred to as Monte Carlo methods. These methods were initially used around the time that the first computers were created and remain pervasive through all fields of science and engineering, including artificial intelligence and machine learning.

Machine learning algorithms relying on deep neural networks recently allowed a great leap forward in artificial intelligence. Despite the popularity of their applications, the efficiency of these algorithms remains largely unexplained from a theoretical point of view. The mathematical description of learning problems involves very large collections of interacting random variables, difficult to handle analytically as well as numerically. This complexity is precisely the object of study of statistical physics. Its mission, originally pointed towards natural systems, is to understand how macroscopic behaviors arise from microscopic laws. Mean-field methods are one type of approximation strategy developed in this view. We review a selection of classical mean-field methods and recent progress relevant for inference in neural networks. In particular, we remind the principles of derivations of high-temperature expansions, the replica method and message passing algorithms, highlighting their equivalences and complementarities. We also provide references for past and current directions of research on neural networks relying on mean-field methods.

Temporal prediction is critical for making intelligent and robust decisions in complex dynamic environments. Motion prediction needs to model the inherently uncertain future which often contains multiple potential outcomes, due to multi-agent interactions and the latent goals of others. Towards these goals, we introduce a probabilistic framework that efficiently learns latent variables to jointly model the multi-step future motions of agents in a scene. Our framework is data-driven and learns semantically meaningful latent variables to represent the multimodal future, without requiring explicit labels. Using a dynamic attention-based state encoder, we learn to encode the past as well as the future interactions among agents, efficiently scaling to any number of agents. Finally, our model can be used for planning via computing a conditional probability density over the trajectories of other agents given a hypothetical rollout of the 'self' agent. We demonstrate our algorithms by predicting vehicle trajectories of both simulated and real data, demonstrating the state-of-the-art results on several vehicle trajectory datasets.

For many applications it is critical to know the uncertainty of a neural network's predictions. While a variety of neural network parameter estimation methods have been proposed for uncertainty estimation, they have not been rigorously compared across uncertainty measures. We assess four of these parameter estimation methods to calibrate uncertainty estimation using four different uncertainty measures: entropy, mutual information, aleatoric uncertainty and epistemic uncertainty. We also evaluate their calibration using expected calibration error. We additionally propose a novel method of neural network parameter estimation called RECAST, which combines cosine annealing with warm restarts with Stochastic Gradient Langevin Dynamics, capturing more diverse parameter distributions. When benchmarked against mutilated data from MNIST, we show that RECAST is well-calibrated and when combined with predictive entropy and epistemic uncertainty it offers the best calibrated measure of uncertainty when compared to recent methods.

Making decisions in the presence of a strategic opponent requires one to take into account the opponent's ability to actively mask its intended objective. To describe such strategic situations, we introduce the non-cooperative inverse reinforcement learning (N-CIRL) formalism. The N-CIRL formalism consists of two agents with completely misaligned objectives, where only one of the agents knows the true objective function. Formally, we model the N-CIRL formalism as a zero-sum Markov game with one-sided incomplete information. Through interacting with the more informed player, the less informed player attempts to both infer, and act according to, the true objective function. As a result of the one-sided incomplete information, the multi-stage game can be decomposed into a sequence of single-stage games expressed by a recursive formula. Solving this recursive formula yields the value of the N-CIRL game and the more informed player's equilibrium strategy. Another recursive formula, constructed by forming an auxiliary game, termed the dual game, yields the less informed player's strategy. Building upon these two recursive formulas, we develop a computationally tractable algorithm to approximately solve for the equilibrium strategies. Finally, we demonstrate the benefits of our N-CIRL formalism over the existing multi-agent IRL formalism via extensive numerical simulation in a novel cyber security setting.

In order to make good decision under uncertainty an agent must learn from observations. To do so, two of the most common frameworks are Contextual Bandits and Markov Decision Processes (MDPs). In this paper, we study whether there exist algorithms for the more general framework (MDP) which automatically provide the best performance bounds for the specific problem at hand without user intervention and without modifying the algorithm. In particular, it is found that a very minor variant of a recently proposed reinforcement learning algorithm for MDPs already matches the best possible regret bound $\tilde O (\sqrt{SAT})$ in the dominant term if deployed on a tabular Contextual Bandit problem despite the agent being agnostic to such setting.

One of the wonderful parts of modern deep learning is the fact that much of it can be understood and used without a full understanding of the mathematics below it. This is a sign of the fact that the field is becoming more mature. Most software developers no longer need to worry about the theory of computable functions, or if programming languages without a goto can emulate programming languages with a goto with at most constant overhead, and neither should the deep learning practitioner need to worry about the theoretical foundations maximum likelihood learning, if one can find an architecture to approximate a target function to an arbitrary degree of accuracy. That said, we are not quite there yet. Sometimes when building a model in practice you will need to understand how architectural choices influence gradient flow, or what assumptions you are making by training with a certain loss function.