Solving Relational MDPs with Exogenous Events and Additive Rewards
Cycorp Inc.（Cycorp公司）；Tufts University（塔夫茨大学）；Oregon State University（俄勒冈州立大学）
S. Joshi, R. Khardon, P. Tadepalli, A. Raghavan, A. Fern
备注：
This is an extended version of our ECML/PKDD 2013 paper including all proofs. (v2 corrects typos and updates ref [10] to cite this report as the full version)
We formalize a simple but natural subclass of service domains for relational planning problems with object-centered, independent exogenous events and additive rewards capturing, for example, problems in inventory control. Focusing on this subclass, we present a new symbolic planning algorithm which is the first algorithm that has explicit performance guarantees for relational MDPs with exogenous events. In particular, under some technical conditions, our planning algorithm provides a monotonic lower bound on the optimal value function. To support this algorithm we present novel evaluation and reduction techniques for generalized first order decision diagrams, a knowledge representation for real-valued functions over relational world states. Our planning algorithm uses a set of focus states, which serves as a training set, to simplify and approximate the symbolic solution, and can thus be seen to perform learning for planning. A preliminary experimental evaluation demonstrates the validity of our approach.
Is Pure Exploitation Sufficient in Exogenous MDPs with Linear Function Approximation?
Department of Informatics, King’s College London（伦敦国王学院信息学院）；Independent Researcher（独立研究者）；Department of Industrial Engineering and Management Sciences, Northwestern University（西北大学工业工程与管理科学系）；The Alan Turing Institute（艾伦·图灵研究所）
KU Leuven（鲁汶大学）；Université libre de Bruxelles（布鲁塞尔自由大学）；Örebro University（厄勒布鲁大学）
Probabilistic model checking has been developed for verifying systems that have stochastic and nondeterministic behavior. Given a probabilistic system, a probabilistic model checker takes a property and checks whether or not the property holds in that system. For this reason, probabilistic model checking provide rigorous guarantees. So far, however, probabilistic model checking has focused on propositional models where a state is represented by a symbol. On the other hand, it is commonly required to make relational abstractions in planning and reinforcement learning. Various frameworks handle …
Relational Markov Decision Processes are a useful abstraction for complex reinforcement learning problems and stochastic planning problems. Recent work developed representation schemes and algorithms for planning in such problems using the value iteration algorithm. However, exact versions of more complex algorithms, including policy iteration, have not been developed or analyzed. The paper investigates this potential and makes several contributions. First we observe two anomalies for relational representations showing that the value of some policies is not well defined or cannot be calculated…
Markov decision processes capture sequential decision making under uncertainty, where an agent must choose actions so as to optimize long term reward. The paper studies efficient reasoning mechanisms for Relational Markov Decision Processes (RMDP) where world states have an internal relational structure that can be naturally described in terms of objects and relations among them. Two contributions are presented. First, the paper develops First Order Decision Diagrams (FODD), a new compact representation for functions over relational structures, together with a set of operators to combine FODDs…
School of Electrical Engineering and Computer Science, Oregon State University（俄勒冈州立大学电气工程与计算机科学学院）；School of Electrical and Computer Engineering, Purdue University（普渡大学电气与计算机工程学院）
We study an approach to policy selection for large relational Markov Decision Processes (MDPs). We consider a variant of approximate policy iteration (API) that replaces the usual value-function learning step with a learning step in policy space. This is advantageous in domains where good policies are easier to represent and learn than the corresponding value functions, which is often the case for the relational MDPs we are interested in. In order to apply API to such problems, we introduce a relational policy language and corresponding learner. In addition, we introduce a new bootstrapping ro…
A Relational Markov Decision Process (RMDP) is a first-order representation to express all instances of a single probabilistic planning domain with possibly unbounded number of objects. Early work in RMDPs outputs generalized (instance-independent) first-order policies or value functions as a means to solve all instances of a domain at once. Unfortunately, this line of work met with limited success due to inherent limitations of the representation space used in such policies or value functions. Can neural models provide the missing link by easily representing more complex generalized policies,…
Oregon State University（俄勒冈州立大学）；University of Notre Dame（圣母大学）
Policy analysts wish to visualize a range of policies for large simulator-defined Markov Decision Processes (MDPs). One visualization approach is to invoke the simulator to generate on-policy trajectories and then visualize those trajectories. When the simulator is expensive, this is not practical, and some method is required for generating trajectories for new policies without invoking the simulator. The method of Model-Free Monte Carlo (MFMC) can do this by stitching together state transitions for a new policy based on previously-sampled trajectories from other policies. This "off-policy Mon…
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）
We address the problem of approximate model minimization for MDPs in which the state is partitioned into endogenous and (much larger) exogenous components. An exogenous state variable is one whose dynamics are independent of the agent's actions. We formalize the mask-learning problem, in which the agent must choose a subset of exogenous state variables to reason about when planning; doing planning in such a reduced state space can often be significantly more efficient than planning in the full model. We then explore the various value functions at play within this setting, and describe conditio…
School of EECS, Oregon State University（俄勒冈州立大学电气与计算机科学学院）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Exogenous state variables and rewards can slow down reinforcement learning by injecting uncontrolled variation into the reward signal. We formalize exogenous state variables and rewards and identify conditions under which an MDP with exogenous state can be decomposed into an exogenous Markov Reward Process involving only the exogenous state+reward and an endogenous Markov Decision Process defined with respect to only the endogenous rewards. We also derive a variance-covariance condition under which Monte Carlo policy evaluation on the endogenous MDP is accelerated compared to using the full MD…
School of Electrical and Computer Engineering, Purdue University（普渡大学电气与计算机工程学院）
We select policies for large Markov Decision Processes (MDPs) with compact first-order representations. We find policies that generalize well as the number of objects in the domain grows, potentially without bound. Existing dynamic-programming approaches based on flat, propositional, or first-order representations either are impractical here or do not naturally scale as the number of objects grows without bound. We implement and evaluate an alternative approach that induces first-order policies using training data constructed by solving small problem instances using PGraphplan (Blum & Langford…
In many practical uses of reinforcement learning (RL) the set of actions available at a given state is a random variable, with realizations governed by an exogenous stochastic process. Somewhat surprisingly, the foundations for such sequential decision processes have been unaddressed. In this work, we formalize and investigate MDPs with stochastic action sets (SAS-MDPs) to provide these foundations. We show that optimal policies and value functions in this model have a structure that admits a compact representation. From an RL perspective, we show that Q-learning with sampled action sets is so…
The Coca-Cola Company（可口可乐公司）；Georgia Institute of Technology（佐治亚理工学院）
We consider a class of sequential decision-making problems under uncertainty that can encompass various types of supervised learning concepts. These problems have a completely observed state process and a partially observed modulation process, where the state process is affected by the modulation process only through an observation process, the observation process only observes the modulation process, and the modulation process is exogenous to control. We model this broad class of problems as a partially observed Markov decision process (POMDP). The belief function for the modulation process i…
