Results 1  10
of
37
Planning under Uncertainty for Robotic Tasks with Mixed Observability
"... Partially observable Markov decision processes (POMDPs) provide a principled, general framework for robot motion planning in uncertain and dynamic environments. They have been applied to various robotic tasks. However, solving POMDPs exactly is computationally intractable. A major challenge is to sc ..."
Abstract

Cited by 44 (4 self)
 Add to MetaCart
(Show Context)
Partially observable Markov decision processes (POMDPs) provide a principled, general framework for robot motion planning in uncertain and dynamic environments. They have been applied to various robotic tasks. However, solving POMDPs exactly is computationally intractable. A major challenge is to scale up POMDP algorithms for complex robotic tasks. Robotic systems often have mixed observability: even when a robot’s state is not fully observable, some components of the state may still be so. We use a factored model to represent separately the fully and partially observable components of a robot’s state and derive a compact lowerdimensional representation of its belief space. This factored representation can be combined with any pointbased algorithm to compute approximate POMDP solutions. Experimental results show that on standard test problems, our approach improves the performance of a leading pointbased POMDP algorithm by many times. 1
Analyzing and Visualizing Multiagent Rewards in Dynamic and Stochastic Environments
 Journal of Autonomous Agents and Multiagent Systems
, 2008
"... Abstract. The ability to analyze the effectiveness of agent reward structures is critical to the successful design of multiagent learning algorithms. Though final system performance is the best indicator of the suitability of a given reward structure, it is often preferable to analyze the reward pro ..."
Abstract

Cited by 37 (29 self)
 Add to MetaCart
(Show Context)
Abstract. The ability to analyze the effectiveness of agent reward structures is critical to the successful design of multiagent learning algorithms. Though final system performance is the best indicator of the suitability of a given reward structure, it is often preferable to analyze the reward properties that lead to good system behavior (i.e., properties promoting coordination among the agents and providing agents with strong signal to noise ratios). This step is particularly helpful in continuous, dynamic, stochastic domains illsuited to simple table backup schemes commonly used in TD(λ)/Qlearning where the effectiveness of the reward structure is difficult to distinguish from the effectiveness of the chosen learning algorithm. In this paper, we present a new reward evaluation method that provides a visualization of the tradeoff between the level of coordination among the agents and the difficulty of the learning problem each agent faces. This method is independent of the learning algorithm and is only a function of the problem domain and the agents’ reward structure. We use this reward property visualization method to determine an effective reward without performing extensive simulations. We then test this method in both a static and a dynamic multirover learning domain where the agents have continuous state spaces and take noisy actions (e.g., the agents ’ movement decisions are not always carried out properly). Our results show that in the more difficult dynamic domain, the reward efficiency visualization method provides a two order of magnitude speedup in selecting good rewards, compared to running a full simulation. In addition, this method facilitates the design and analysis of new rewards tailored to the observational limitations of the domain, providing rewards that combine the best properties of traditional rewards. 1.
Solving factored MDPs with hybrid state and action variables
 J. Artif. Intell. Res. (JAIR
"... Efficient representations and solutions for large decision problems with continuous and discrete variables are among the most important challenges faced by the designers of automated decision support systems. In this paper, we describe a novel hybrid factored Markov decision process (MDP) model tha ..."
Abstract

Cited by 29 (4 self)
 Add to MetaCart
(Show Context)
Efficient representations and solutions for large decision problems with continuous and discrete variables are among the most important challenges faced by the designers of automated decision support systems. In this paper, we describe a novel hybrid factored Markov decision process (MDP) model that allows for a compact representation of these problems, and a new hybrid approximate linear programming (HALP) framework that permits their efficient solutions. The central idea of HALP is to approximate the optimal value function by a linear combination of basis functions and optimize its weights by linear programming. We analyze both theoretical and computational aspects of this approach, and demonstrate its scaleup potential on several hybrid optimization problems. 1.
Practical solution techniques for firstorder mdps
 Artificial Intelligence
"... Many traditional solution approaches to relationally specified decisiontheoretic planning problems (e.g., those stated in the probabilistic planning domain description language, or PPDDL) ground the specification with respect to a specific instantiation of domain objects and apply a solution approa ..."
Abstract

Cited by 25 (1 self)
 Add to MetaCart
(Show Context)
Many traditional solution approaches to relationally specified decisiontheoretic planning problems (e.g., those stated in the probabilistic planning domain description language, or PPDDL) ground the specification with respect to a specific instantiation of domain objects and apply a solution approach directly to the resulting ground Markov decision process (MDP). Unfortunately, the space and time complexity of these grounded solution approaches are polynomial in the number of domain objects and exponential in the predicate arity and the number of nested quantifiers in the relational problem specification. An alternative to grounding a relational planning problem is to tackle the problem directly at the relational level. In this article, we propose one such approach that translates an expressive subset of the PPDDL representation to a firstorder MDP (FOMDP) specification and then derives a domainindependent policy without grounding at any intermediate step. However, such generality does not come without its own set of challenges—the purpose of this article is to explore practical solution techniques for solving FOMDPs. To demonstrate the applicability of our techniques, we present proofofconcept results of our firstorder approximate linear programming (FOALP) planner on problems from the probabilistic track
A CostShaping Linear Program for AverageCost Approximate Dynamic Programming with Performance Guarantees
, 2006
"... ..."
(Show Context)
An mcmc approach to solving hybrid factored mdps
 In Proceedings of the 19th International Joint Conference on Artificial Intelligence
, 2005
"... Hybrid approximate linear programming (HALP) has recently emerged as a promising framework for solving large factored Markov decision processes (MDPs) with discrete and continuous state and action variables. Our work addresses its major computational bottleneck – constraint satisfaction in large s ..."
Abstract

Cited by 17 (9 self)
 Add to MetaCart
Hybrid approximate linear programming (HALP) has recently emerged as a promising framework for solving large factored Markov decision processes (MDPs) with discrete and continuous state and action variables. Our work addresses its major computational bottleneck – constraint satisfaction in large structured domains of discrete and continuous variables. We analyze this problem and propose a novel Markov chain Monte Carlo (MCMC) method for finding the most violated constraint of a relaxed HALP. This method does not require the discretization of continuous variables, searches the space of constraints intelligently based on the structure of factored MDPs, and its space complexity is linear in the number of variables. We test the method on a set of large control problems and demonstrate improvements over alternative approaches. 1
Solving factored MDPs with exponentialfamily transition models
 In Proceedings of the 16th International Conference on Automated Planning and Scheduling (ICAPS
, 2006
"... Markov decision processes (MDPs) with discrete and continuous state and action components can be solved efficiently by hybrid approximate linear programming (HALP). The main idea of the approach is to approximate the optimal value function by a linear combination of basis functions and optimize it b ..."
Abstract

Cited by 12 (9 self)
 Add to MetaCart
Markov decision processes (MDPs) with discrete and continuous state and action components can be solved efficiently by hybrid approximate linear programming (HALP). The main idea of the approach is to approximate the optimal value function by a linear combination of basis functions and optimize it by linear programming. In this paper, we extend the existing HALP paradigm beyond the mixture of beta transition model. As a result, we permit modeling of other transition functions, such as normal and gamma densities, without approximating them. To allow for efficient solutions to the expectation terms in HALP, we identify a rich class of conjugate basis functions. Finally, we demonstrate the generalized HALP framework on a rover planning problem, which exhibits continuous time and resource uncertainty.
Firstorder decisiontheoretic planning in structured relational environments
, 2008
"... We consider the general framework of firstorder decisiontheoretic planning in structured relational environments. Most traditional solution approaches to these planning problems ground the relational specification w.r.t. a specific domain instantiation and apply a solution approach directly to the ..."
Abstract

Cited by 10 (2 self)
 Add to MetaCart
We consider the general framework of firstorder decisiontheoretic planning in structured relational environments. Most traditional solution approaches to these planning problems ground the relational specification w.r.t. a specific domain instantiation and apply a solution approach directly to the resulting ground Markov decision process (MDP). Unfortunately, the space and time complexity of these solution algorithms scale linearly with the domain size in the best case and exponentially in the worst case. An alternate approach to grounding a relational planning problem is to lift it to a firstorder MDP (FOMDP) specification. This FOMDP can then be solved directly, resulting in a domainindependent solution whose space and time complexity either do not scale with domain size or can scale sublinearly in the domain size. However, such generality does not come without its own set of challenges and the first purpose of this thesis is to explore exact and approximate solution techniques for practically solving FOMDPs. The second purpose of this thesis is to extend the FOMDP specification to succinctly capture factored actions and additive rewards while extending the exact and approximate solution techniques to directly exploit this structure. In addition, we provide a proof of correctness of the firstorder symbolic dynamic programming approach w.r.t. its wellstudied ground MDP
Automatic Feature Selection for ModelBased Reinforcement Learning in Factored MDPs
"... Abstract—Feature selection is an important challenge in machine learning. Unfortunately, most methods for automating feature selection are designed for supervised learning tasks and are thus either inapplicable or impractical for reinforcement learning. This paper presents a new approach to feature ..."
Abstract

Cited by 9 (3 self)
 Add to MetaCart
(Show Context)
Abstract—Feature selection is an important challenge in machine learning. Unfortunately, most methods for automating feature selection are designed for supervised learning tasks and are thus either inapplicable or impractical for reinforcement learning. This paper presents a new approach to feature selection specifically designed for the challenges of reinforcement learning. In our method, the agent learns a model, represented as a dynamic Bayesian network, of a factored Markov decision process, deduces a minimal feature set from this network, and efficiently computes a policy on this feature set using dynamic programming methods. Experiments in a stocktrading benchmark task demonstrate that this approach can reliably deduce minimal feature sets and that doing so can substantially improve performance and reduce the computational expense of planning. KeywordsReinforcement learning; feature selection; factored MDPs I.
Learning Basis Functions in Hybrid Domains
 In Proceedings of the 2006 National Conference on Artificial Intelligence (AAAI
, 2006
"... Markov decision processes (MDPs) with discrete and continuous state and action components can be solved efficiently by hybrid approximate linear programming (HALP). The main idea of the approach is to approximate the optimal value function by a set of basis functions and optimize their weights by li ..."
Abstract

Cited by 6 (2 self)
 Add to MetaCart
Markov decision processes (MDPs) with discrete and continuous state and action components can be solved efficiently by hybrid approximate linear programming (HALP). The main idea of the approach is to approximate the optimal value function by a set of basis functions and optimize their weights by linear programming. The quality of this approximation naturally depends on its basis functions. However, basis functions leading to good approximations are rarely known in advance. In this paper, we propose a new approach that discovers these functions automatically. The method relies on a class of parametric basis function models, which are optimized using the dual formulation of a relaxed HALP. We demonstrate the performance of our method on two hybrid optimization problems and compare it to manually selected basis functions.