scholarly journals Building Personalized Simulator for Interactive Search

2019 ◽  
Author(s):  
Qianlong Liu ◽  
Baoliang Cui ◽  
Zhongyu Wei ◽  
Baolin Peng ◽  
Haikuan Huang ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Real World ◽  
Decision Problem ◽  
Online Training ◽  
Sequential Decision ◽  
Information Need ◽  
Interactive Search ◽  
Search Results ◽  
Two Stages ◽  
Cold Start Problem

Interactive search, where a set of tags is recommended to users together with search results at each turn, is an effective way to guide users to identify their information need. It is a classical sequential decision problem and the reinforcement learning based agent can be introduced as a solution. The training of the agent can be divided into two stages, i.e., offline and online. Existing reinforcement learning based systems tend to perform the offline training in a supervised way based on historical labeled data while the online training is performed via reinforcement learning algorithms based on interactions with real users. The mis-match between online and offline training leads to a cold-start problem for the online usage of the agent. To address this issue, we propose to employ a simulator to mimic the environment for the offline training of the agent. Users' profiles are considered to build a personalized simulator, besides, model-based approach is used to train the simulator and is able to use the data efficiently. Experimental results based on real-world dataset demonstrate the effectiveness of our agent and personalized simulator.

scholarly journals Intelligent Inventory Control via Ruminative Reinforcement Learning

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Tatpong Katanyukul ◽  
Edwin K. P. Chong
Keyword(s):  
Reinforcement Learning ◽  
Inventory Control ◽  
Inventory Management ◽  
Decision Problem ◽  
Domain Knowledge ◽  
Problem Structure ◽  
Sequential Decision ◽  
Conventional Form ◽  
New Methods ◽  
Insight Into

Inventory management is a sequential decision problem that can be solved with reinforcement learning (RL). Although RL in its conventional form does not require domain knowledge, exploiting such knowledge of problem structure, usually available in inventory management, can be beneficial to improving the learning quality and speed of RL. Ruminative reinforcement learning (RRL) has been introduced recently based on this approach. RRL is motivated by how humans contemplate the consequences of their actions in trying to learn how to make a better decision. This study further investigates the issues of RRL and proposes new RRL methods applied to inventory management. Our investigation provides insight into different RRL characteristics, and our experimental results show the viability of the new methods.

scholarly journals Reinforcement Learning with a Corrupted Reward Channel

2017 ◽  
Author(s):  
Tom Everitt ◽  
Victoria Krakovna ◽  
Laurent Orseau ◽  
Shane Legg
Keyword(s):  
Reinforcement Learning ◽  
Real World ◽  
Decision Problem ◽  
Inverse Reinforcement Learning ◽  
Markov Decision Problem ◽  
Software Bugs ◽  
Reward Function ◽  
Learning Agent ◽  
Markov Decision ◽  
Simplifying Assumptions

No real-world reward function is perfect. Sensory errors and software bugs may result in agents getting higher (or lower) rewards than they should. For example, a reinforcement learning agent may prefer states where a sensory error gives it the maximum reward, but where the true reward is actually small. We formalise this problem as a generalised Markov Decision Problem called Corrupt Reward MDP. Traditional RL methods fare poorly in CRMDPs, even under strong simplifying assumptions and when trying to compensate for the possibly corrupt rewards. Two ways around the problem are investigated. First, by giving the agent richer data, such as in inverse reinforcement learning and semi-supervised reinforcement learning, reward corruption stemming from systematic sensory errors may sometimes be completely managed. Second, by using randomisation to blunt the agent's optimisation, reward corruption can be partially managed under some assumptions.

scholarly journals Real-World Reinforcement Learning: Observations from Two Successful Cases

2021 ◽  
Author(s):  
Philipp Back ◽  
Keyword(s):  
Reinforcement Learning ◽  
Real World ◽  
Secondary Data ◽  
Optimal Strategies ◽  
Sequential Decision ◽  
Agent Behavior ◽  
Reward Function ◽  
Data Center Cooling ◽  
Safety Constraints ◽  
Order Execution

Reinforcement Learning (RL) is a machine learning technique that enables artificial agents to learn optimal strategies for sequential decision-making problems. RL has achieved superhuman performance in artificial domains, yet real-world applications remain rare. We explore the drivers of successful RL adoption for solving practical business problems. We rely on publicly available secondary data on two cases: data center cooling at Google and trade order execution at JPMorgan. We perform thematic analysis using a pre-defined coding framework based on the known challenges to real-world RL by DulacArnold, Mankowitz, & Hester (2019). First, we find that RL works best when the problem dynamics can be simulated. Second, the ability to encode the desired agent behavior as a reward function is critical. Third, safety constraints are often necessary in the context of trial-and-error learning. Our work is amongst the first in Information Systems to discuss the practical business value of the emerging AI subfield of RL.

Recent Advances in Reinforcement Learning for Traffic Signal Control

2021 ◽  
Vol 22 (2) ◽  
pp. 12-18 ◽  
Author(s):  
Hua Wei ◽  
Guanjie Zheng ◽  
Vikash Gayah ◽  
Zhenhui Li
Keyword(s):  
Reinforcement Learning ◽  
Real World ◽  
Intelligent Transportation Systems ◽  
Transportation Systems ◽  
Traffic Signal ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Control Methods ◽  
Advantages And Disadvantages ◽  
Recent Advances

Traffic signal control is an important and challenging real-world problem that has recently received a large amount of interest from both transportation and computer science communities. In this survey, we focus on investigating the recent advances in using reinforcement learning (RL) techniques to solve the traffic signal control problem. We classify the known approaches based on the RL techniques they use and provide a review of existing models with analysis on their advantages and disadvantages. Moreover, we give an overview of the simulation environments and experimental settings that have been developed to evaluate the traffic signal control methods. Finally, we explore future directions in the area of RLbased traffic signal control methods. We hope this survey could provide insights to researchers dealing with real-world applications in intelligent transportation systems

Challenges of real-world reinforcement learning: definitions, benchmarks and analysis

2021 ◽  
Author(s):  
Gabriel Dulac-Arnold ◽  
Nir Levine ◽  
Daniel J. Mankowitz ◽  
Jerry Li ◽  
Cosmin Paduraru ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Real World

scholarly journals Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems

2021 ◽  
Author(s):  
Amarildo Likmeta ◽  
Alberto Maria Metelli ◽  
Giorgia Ramponi ◽  
Andrea Tirinzoni ◽  
Matteo Giuliani ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Real World ◽  
Real Life ◽  
User Preferences ◽  
Inverse Reinforcement Learning ◽  
Water Release ◽  
Reward Function ◽  
Model Free ◽  
Conflicting Objectives ◽  
Multiple Experts

AbstractIn real-world applications, inferring the intentions of expert agents (e.g., human operators) can be fundamental to understand how possibly conflicting objectives are managed, helping to interpret the demonstrated behavior. In this paper, we discuss how inverse reinforcement learning (IRL) can be employed to retrieve the reward function implicitly optimized by expert agents acting in real applications. Scaling IRL to real-world cases has proved challenging as typically only a fixed dataset of demonstrations is available and further interactions with the environment are not allowed. For this reason, we resort to a class of truly batch model-free IRL algorithms and we present three application scenarios: (1) the high-level decision-making problem in the highway driving scenario, and (2) inferring the user preferences in a social network (Twitter), and (3) the management of the water release in the Como Lake. For each of these scenarios, we provide formalization, experiments and a discussion to interpret the obtained results.

scholarly journals Selective network discovery via deep reinforcement learning on embedded spaces

2021 ◽  
Vol 6 (1) ◽  
Author(s):  
Peter Morales ◽  
Rajmonda Sulo Caceres ◽  
Tina Eliassi-Rad
Keyword(s):  
Reinforcement Learning ◽  
Learning Algorithm ◽  
Sequential Decision ◽  
Network Discovery ◽  
Learning Tasks ◽  
Partially Observed ◽  
Decision Making Problem ◽  
Resource Collection ◽  
Improved Performance ◽  
Discovery Algorithms

AbstractComplex networks are often either too large for full exploration, partially accessible, or partially observed. Downstream learning tasks on these incomplete networks can produce low quality results. In addition, reducing the incompleteness of the network can be costly and nontrivial. As a result, network discovery algorithms optimized for specific downstream learning tasks given resource collection constraints are of great interest. In this paper, we formulate the task-specific network discovery problem as a sequential decision-making problem. Our downstream task is selective harvesting, the optimal collection of vertices with a particular attribute. We propose a framework, called network actor critic (NAC), which learns a policy and notion of future reward in an offline setting via a deep reinforcement learning algorithm. The NAC paradigm utilizes a task-specific network embedding to reduce the state space complexity. A detailed comparative analysis of popular network embeddings is presented with respect to their role in supporting offline planning. Furthermore, a quantitative study is presented on various synthetic and real benchmarks using NAC and several baselines. We show that offline models of reward and network discovery policies lead to significantly improved performance when compared to competitive online discovery algorithms. Finally, we outline learning regimes where planning is critical in addressing sparse and changing reward signals.

scholarly journals Non Stationary Multi-Armed Bandit: Empirical Evaluation of a New Concept Drift-Aware Algorithm

Entropy ◽  
2021 ◽  
Vol 23 (3) ◽  
pp. 380
Author(s):  
Emanuele Cavenaghi ◽  
Gabriele Sottocornola ◽  
Fabio Stella ◽  
Markus Zanker
Keyword(s):  
Real World ◽  
Concept Drift ◽  
Empirical Evaluation ◽  
Sliding Window ◽  
Discount Factor ◽  
Data Streaming ◽  
Sources Of Information ◽  
Sequential Decision ◽  
Time Step ◽  
Thompson Sampling

The Multi-Armed Bandit (MAB) problem has been extensively studied in order to address real-world challenges related to sequential decision making. In this setting, an agent selects the best action to be performed at time-step t, based on the past rewards received by the environment. This formulation implicitly assumes that the expected payoff for each action is kept stationary by the environment through time. Nevertheless, in many real-world applications this assumption does not hold and the agent has to face a non-stationary environment, that is, with a changing reward distribution. Thus, we present a new MAB algorithm, named f-Discounted-Sliding-Window Thompson Sampling (f-dsw TS), for non-stationary environments, that is, when the data streaming is affected by concept drift. The f-dsw TS algorithm is based on Thompson Sampling (TS) and exploits a discount factor on the reward history and an arm-related sliding window to contrast concept drift in non-stationary environments. We investigate how to combine these two sources of information, namely the discount factor and the sliding window, by means of an aggregation function f(.). In particular, we proposed a pessimistic (f=min), an optimistic (f=max), as well as an averaged (f=mean) version of the f-dsw TS algorithm. A rich set of numerical experiments is performed to evaluate the f-dsw TS algorithm compared to both stationary and non-stationary state-of-the-art TS baselines. We exploited synthetic environments (both randomly-generated and controlled) to test the MAB algorithms under different types of drift, that is, sudden/abrupt, incremental, gradual and increasing/decreasing drift. Furthermore, we adapt four real-world active learning tasks to our framework—a prediction task on crimes in the city of Baltimore, a classification task on insects species, a recommendation task on local web-news, and a time-series analysis on microbial organisms in the tropical air ecosystem. The f-dsw TS approach emerges as the best performing MAB algorithm. At least one of the versions of f-dsw TS performs better than the baselines in synthetic environments, proving the robustness of f-dsw TS under different concept drift types. Moreover, the pessimistic version (f=min) results as the most effective in all real-world tasks.

scholarly journals Optimal Policies for Quantum Markov Decision Processes

2021 ◽  
Author(s):  
Ming-Sheng Ying ◽  
Yuan Feng ◽  
Sheng-Gang Ying
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Quantum Systems ◽  
Sequential Decision Making ◽  
Mathematical Framework ◽  
Sequential Decision ◽  
Learning Techniques ◽  
Optimal Policies ◽  
Markov Decision ◽  
Programming Algorithms

AbstractMarkov decision process (MDP) offers a general framework for modelling sequential decision making where outcomes are random. In particular, it serves as a mathematical framework for reinforcement learning. This paper introduces an extension of MDP, namely quantum MDP (qMDP), that can serve as a mathematical model of decision making about quantum systems. We develop dynamic programming algorithms for policy evaluation and finding optimal policies for qMDPs in the case of finite-horizon. The results obtained in this paper provide some useful mathematical tools for reinforcement learning techniques applied to the quantum world.

scholarly journals Goal-driven active learning

2021 ◽  
Vol 35 (2) ◽  
Author(s):  
Nicolas Bougie ◽  
Ryutaro Ichise
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Learning Process ◽  
Real World ◽  
Imitation Learning ◽  
Learning Approaches ◽  
Wide Range ◽  
Fixed Set ◽  
Complex Decision Making ◽  
Complex Decision

AbstractDeep reinforcement learning methods have achieved significant successes in complex decision-making problems. In fact, they traditionally rely on well-designed extrinsic rewards, which limits their applicability to many real-world tasks where rewards are naturally sparse. While cloning behaviors provided by an expert is a promising approach to the exploration problem, learning from a fixed set of demonstrations may be impracticable due to lack of state coverage or distribution mismatch—when the learner’s goal deviates from the demonstrated behaviors. Besides, we are interested in learning how to reach a wide range of goals from the same set of demonstrations. In this work we propose a novel goal-conditioned method that leverages very small sets of goal-driven demonstrations to massively accelerate the learning process. Crucially, we introduce the concept of active goal-driven demonstrations to query the demonstrator only in hard-to-learn and uncertain regions of the state space. We further present a strategy for prioritizing sampling of goals where the disagreement between the expert and the policy is maximized. We evaluate our method on a variety of benchmark environments from the Mujoco domain. Experimental results show that our method outperforms prior imitation learning approaches in most of the tasks in terms of exploration efficiency and average scores.

Sign in / Sign up

Export Citation Format

Share Document