اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدInverse Reinforcement Learning with Multiple Ranked Experts
133
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
We consider the problem of learning to behave optimally in a Markov Decision Process when a reward function is not specified, but instead we have access to a set of demonstrators of varying performance. We assume the demonstrators are classified into one of k ranks, and use ideas from ordinal regression to find a reward function that maximizes the margin between the different ranks. This approach is based on the idea that agents should not only learn how to behave from experts, but also how not to behave from non-experts. We show there are MDPs where important differences in the reward function would be hidden from existing algorithms by the behaviour of the expert. Our method is particularly useful for problems where we have access to a large set of agent behaviours with varying degrees of expertise (such as through GPS or cellphones). We highlight the differences between our approach and existing methods using a simple grid domain and demonstrate its efficacy on determining passenger-finding strategies for taxi drivers, using a large dataset of GPS trajectories.
قيم البحث
اقرأ أيضاً
It has been well demonstrated that inverse reinforcement learning (IRL) is an effective technique for teaching machines to perform tasks at human skill levels given human demonstrations (i.e., human to machine apprenticeship learning). This paper see
ks to show that a similar application can be demonstrated with human learners. That is, given demonstrations from human experts inverse reinforcement learning techniques can be used to teach other humans to perform at higher skill levels (i.e., human to human apprenticeship learning). To show this two experiments were conducted using a simple, real-time web game where players were asked to touch targets in order to earn as many points as possible. For the experiment player performance was defined as the number of targets a player touched, irrespective of the points that a player actually earned. This allowed for in-game points to be modified and the effect of these alterations on performance measured. At no time were participants told the true performance metric. To determine the point modifications IRL was applied on demonstrations of human experts playing the game. The results of the experiment show with significance that performance improved over the control for select treatment groups. Finally, in addition to the experiment, we also detail the algorithmic challenges we faced when conducting the experiment and the techniques we used to overcome them.
Agent-based methods allow for defining simple rules that generate complex group behaviors. The governing rules of such models are typically set a priori and parameters are tuned from observed behavior trajectories. Instead of making simplifying assum
ptions across all anticipated scenarios, inverse reinforcement learning provides inference on the short-term (local) rules governing long term behavior policies by using properties of a Markov decision process. We use the computationally efficient linearly-solvable Markov decision process to learn the local rules governing collective movement for a simulation of the self propelled-particle (SPP) model and a data application for a captive guppy population. The estimation of the behavioral decision costs is done in a Bayesian framework with basis function smoothing. We recover the true costs in the SPP simulation and find the guppies value collective movement more than targeted movement toward shelter.
A significant challenge for the practical application of reinforcement learning in the real world is the need to specify an oracle reward function that correctly defines a task. Inverse reinforcement learning (IRL) seeks to avoid this challenge by in
stead inferring a reward function from expert behavior. While appealing, it can be impractically expensive to collect datasets of demonstrations that cover the variation common in the real world (e.g. opening any type of door). Thus in practice, IRL must commonly be performed with only a limited set of demonstrations where it can be exceedingly difficult to unambiguously recover a reward function. In this work, we exploit the insight that demonstrations from other tasks can be used to constrain the set of possible reward functions by learning a prior that is specifically optimized for the ability to infer expressive reward functions from limited numbers of demonstrations. We demonstrate that our method can efficiently recover rewards from images for novel tasks and provide intuition as to how our approach is analogous to learning a prior.
In many real life situations, including job and loan applications, gatekeepers must make justified and fair real-time decisions about a persons fitness for a particular opportunity. In this paper, we aim to accomplish approximate group fairness in an
online stochastic decision-making process, where the fairness metric we consider is equalized odds. Our work follows from the classical learning-from-experts scheme, assuming a finite set of classifiers (human experts, rules, options, etc) that cannot be modified. We run separate instances of the algorithm for each label class as well as sensitive groups, where the probability of choosing each instance is optimized for both fairness and regret. Our theoretical results show that approximately equalized odds can be achieved without sacrificing much regret. We also demonstrate the performance of the algorithm on real data sets commonly used by the fairness community.
The goal of the inverse reinforcement learning (IRL) problem is to recover the reward functions from expert demonstrations. However, the IRL problem like any ill-posed inverse problem suffers the congenital defect that the policy may be optimal for m
any reward functions, and expert demonstrations may be optimal for many policies. In this work, we generalize the IRL problem to a well-posed expectation optimization problem stochastic inverse reinforcement learning (SIRL) to recover the probability distribution over reward functions. We adopt the Monte Carlo expectation-maximization (MCEM) method to estimate the parameter of the probability distribution as the first solution to the SIRL problem. The solution is succinct, robust, and transferable for a learning task and can generate alternative solutions to the IRL problem. Through our formulation, it is possible to observe the intrinsic property for the IRL problem from a global viewpoint, and our approach achieves a considerable performance on the objectworld.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
