Model-based reinforcement learning (MBRL) can significantly improve sample efficiency, particularly when carefully choosing the states from which to sample hypothetical transitions. Such prioritization has been empirically shown to be useful for both experience replay (ER) and Dyna-style planning. However, there is as yet little theoretical understanding in RL about such prioritization strategies, and why they help. In this work, we revisit prioritized ER and, in an ideal setting, show an equivalence to minimizing cubic loss, providing theoretical insight into why it improves upon uniform sampling. This ideal setting, however, cannot be realized in practice, due to insufficient coverage of the sample space and outdated priorities of training samples. This motivates our model-based approach, which does not suffer from these limitations. Our key idea is to actively search for high priority states using gradient ascent. Under certain conditions, we prove that the distribution of hypothetical experiences generated from these states provides a diverse set of states, sampled proportionally to approximately true priorities. Our experiments on both benchmark and application-oriented domain show that our approach achieves superior performance over both the model-free prioritized ER method and several closely related model-based baselines.

Human attention is a scarce resource in modern computing. A multitude of microtasks vie for user attention to crowdsource information, perform momentary assessments, personalize services, and execute actions with a single touch. A lot gets done when these tasks take up the invisible free moments of the day. However, an interruption at an inappropriate time degrades productivity and causes annoyance. Prior works have exploited contextual cues and behavioral data to identify interruptibility for microtasks with much success. With Quick Question, we explore use of reinforcement learning (RL) to schedule microtasks while minimizing user annoyance and compare its performance with supervised learning. We model the problem as a Markov decision process and use Advantage Actor Critic algorithm to identify interruptible moments based on context and history of user interactions. In our 5-week, 30-participant study, we compare the proposed RL algorithm against supervised learning methods. While the mean number of responses between both methods is commensurate, RL is more effective at avoiding dismissal of notifications and improves user experience over time.

The demand for same-day delivery (SDD) has increased rapidly in the last few years and has particularly boomed during the COVID-19 pandemic. Existing literature on the problem has focused on maximizing the utility, represented as the total number of expected requests served. However, a utility-driven solution results in unequal opportunities for customers to receive delivery service, raising questions about fairness. In this paper, we study the problem of achieving fairness in SDD. We construct a regional-level fairness constraint that ensures customers from different regions have an equal chance of being served. We develop a reinforcement learning model to learn policies that focus on both overall utility and fairness. Experimental results demonstrate the ability of our approach to mitigate the unfairness caused by geographic differences and constraints of resources, at both coarser and finer-grained level and with a small cost to utility. In addition, we simulate a real-world situation where the system is suddenly overwhelmed by a surge of requests, mimicking the COVID-19 scenario. Our model is robust to the systematic pressure and is able to maintain fairness with little compromise to the utility.

Assistance games (also known as cooperative inverse reinforcement learning games) have been proposed as a model for beneficial AI, wherein a robotic agent must act on behalf of a human principal but is initially uncertain about the humans payoff function. This paper studies multi-principal assistance games, which cover the more general case in which the robot acts on behalf of N humans who may have widely differing payoffs. Impossibility theorems in social choice theory and voting theory can be applied to such games, suggesting that strategic behavior by the human principals may complicate the robots task in learning their payoffs. We analyze in particular a bandit apprentice game in which the humans act first to demonstrate their individual preferences for the arms and then the robot acts to maximize the sum of human payoffs. We explore the extent to which the cost of choosing suboptimal arms reduces the incentive to mislead, a form of natural mechanism design. In this context we propose a social choice method that uses shared control of a system to combine preference inference with social welfare optimization.

Free Coupon Discount - Artificial Intelligence for Business, Solve Real World Business Problems with AI Solutions Created by Hadelin de Ponteves Kirill Eremenko SuperDataScience Team Students also bought Unsupervised Deep Learning in Python Cluster Analysis and Unsupervised Machine Learning in Python Advanced AI: Deep Reinforcement Learning in Python Cutting-Edge AI: Deep Reinforcement Learning in Python Deep Learning: Recurrent Neural Networks in Python Deep Learning Prerequisites: Linear Regression in Python Preview this Udemy Course GET COUPON CODE Description Structure of the course: Part 1 - Optimizing Business Processes Case Study: Optimizing the Flows in an E-Commerce Warehouse AI Solution: Q-Learning Part 2 - Minimizing Costs Case Study: Minimizing the Costs in Energy Consumption of a Data Center AI Solution: Deep Q-Learning Part 3 - Maximizing Revenues Case Study: Maximizing Revenue of an Online Retail Business AI Solution: Thompson Sampling Real World Business Applications: With Artificial Intelligence, you can do three main things for any business: Optimize Business Processes Minimize Costs Maximize Revenues We will show you exactly how to succeed these applications, through Real World Business case studies. And for each of these applications we will build a separate AI to solve the challenge. In Part 1 - Optimizing Processes, we will build an AI that will optimize the flows in an E-Commerce warehouse. In Part 2 - Minimizing Costs, we will build a more advanced AI that will minimize the costs in energy consumption of a data center by more than 50%! Just as Google did last year thanks to DeepMind.

The ability to quickly solve a wide range of real-world tasks requires a commonsense understanding of the world. Yet, how to best extract such knowledge from natural language corpora and integrate it with reinforcement learning (RL) agents remains an open challenge. This is partly due to the lack of lightweight simulation environments that sufficiently reflect the semantics of the real world and provide knowledge sources grounded with respect to observations in an RL environment. To better enable research on agents making use of commonsense knowledge, we propose WordCraft, an RL environment based on Little Alchemy 2. This lightweight environment is fast to run and built upon entities and relations inspired by real-world semantics. We evaluate several representation learning methods on this new benchmark and propose a new method for integrating knowledge graphs with an RL agent.

In this thesis, I propose a family of fully decentralized deep multi-agent reinforcement learning (MARL) algorithms to achieve high, real-time performance in network-level traffic signal control. In this approach, each intersection is modeled as an agent that plays a Markovian Game against the other intersection nodes in a traffic signal network modeled as an undirected graph, to approach the optimal reduction in delay. Following Partially Observable Markov Decision Processes (POMDPs), there are 3 levels of communication schemes between adjacent learning agents: independent deep Q-leaning (IDQL), shared states reinforcement learning (S2RL) and a shared states & rewards version of S2RL--S2R2L. In these 3 variants of decentralized MARL schemes, individual agent trains its local deep Q network (DQN) separately, enhanced by convergence-guaranteed techniques like double DQN, prioritized experience replay, multi-step bootstrapping, etc. To test the performance of the proposed three MARL algorithms, a SUMO-based simulation platform is developed to mimic the traffic evolution of the real world. Fed with random traffic demand between permitted OD pairs, a 4x4 Manhattan-style grid network is set up as the testbed, two different vehicle arrival rates are generated for model training and testing. The experiment results show that S2R2L has a quicker convergence rate and better convergent performance than IDQL and S2RL in the training process. Moreover, three MARL schemes all reveal exceptional generalization abilities. Their testing results surpass the benchmark Max Pressure (MP) algorithm, under the criteria of average vehicle delay, network-level queue length and fuel consumption rate. Notably, S2R2L has the best testing performance of reducing 34.55% traffic delay and dissipating 10.91% queue length compared with MP.

Offline reinforcement learning (RL purely from logged data) is an important avenue for deploying RL techniques in real-world scenarios. However, existing hyperparameter selection methods for offline RL break the offline assumption by evaluating policies corresponding to each hyperparameter setting in the environment. This online execution is often infeasible and hence undermines the main aim of offline RL. Therefore, in this work, we focus on \textit{offline hyperparameter selection}, i.e. methods for choosing the best policy from a set of many policies trained using different hyperparameters, given only logged data. Through large-scale empirical evaluation we show that: 1) offline RL algorithms are not robust to hyperparameter choices, 2) factors such as the offline RL algorithm and method for estimating Q values can have a big impact on hyperparameter selection, and 3) when we control those factors carefully, we can reliably rank policies across hyperparameter choices, and therefore choose policies which are close to the best policy in the set. Overall, our results present an optimistic view that offline hyperparameter selection is within reach, even in challenging tasks with pixel observations, high dimensional action spaces, and long horizon.

We revisit the role of instrumental value as a driver of adaptive behavior. In active inference, instrumental or extrinsic value is quantified by the information-theoretic surprisal of a set of observations measuring the extent to which those observations conform to prior beliefs or preferences. That is, an agent is expected to seek the type of evidence that is consistent with its own model of the world. For reinforcement learning tasks, the distribution of preferences replaces the notion of reward. We explore a scenario in which the agent learns this distribution in a self-supervised manner. In particular, we highlight the distinction between observations induced by the environment and those pertaining more directly to the continuity of an agent in time. We evaluate our methodology in a dynamic environment with discrete time and actions. First with a surprisal minimizing model-free agent (in the RL sense) and then expanding to the model-based case to minimize the expected free energy.

Reinforcement learning (RL) algorithms update an agent's parameters according to one of several possible rules, discovered manually through years of research. Automating the discovery of update rules from data could lead to more efficient algorithms, or algorithms that are better adapted to specific environments. Although there have been prior attempts at addressing this significant scientific challenge, it remains an open question whether it is feasible to discover alternatives to fundamental concepts of RL such as value functions and temporal-difference learning. This paper introduces a new meta-learning approach that discovers an entire update rule which includes both 'what to predict' (e.g. value functions) and 'how to learn from it' (e.g. bootstrapping) by interacting with a set of environments. The output of this method is an RL algorithm that we call Learned Policy Gradient (LPG). Empirical results show that our method discovers its own alternative to the concept of value functions. Furthermore it discovers a bootstrapping mechanism to maintain and use its predictions. Surprisingly, when trained solely on toy environments, LPG generalises effectively to complex Atari games and achieves non-trivial performance. This shows the potential to discover general RL algorithms from data.