Planning and acting in partially observable stochastic domains

DOI10.1016/S0004-3702(98)00023-XzbMATH Open0908.68165DBLPjournals/ai/KaelblingLC98OpenAlexW2168359464WikidataQ56602944 ScholiaQ56602944MaRDI QIDQ72343FDOQ72343

Authors: Leslie Pack Kaelbling, Michael L. Littman, Anthony R. Cassandra, Leslie Pack Kaelbling, Michael L. Littman, Anthony R. Cassandra 

Publication date: May 1998

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0004-3702(98)00023-x

Recommendations

• Planning in partially-observable switching-mode continuous domains
• scientific article; zbMATH DE number 5547912
• Strong planning under partial observability
• Learning and planning in partially observable environments without prior domain knowledge
• Replanning in domains with partial information and sensing actions
• Randomized belief-space replanning in partially-observable continuous spaces

zbMATH Keywords

partially observable Markov decision processesplanninguncertainty

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Cites Work

• Fast planning through planning graph analysis
• The complexity of stochastic games
• The complexity of mean payoff games on graphs
• Optimal control of Markov processes with incomplete state information
• A survey of algorithmic methods for partially observed Markov decision processes
• Solving H-horizon, stationary Markov decision problems in time proportional to log (H)
• Title not available (Why is that?)
• The Optimal Search for a Moving Target When the Search Path Is Constrained
• Title not available (Why is that?)
• State of the Art—A Survey of Partially Observable Markov Decision Processes: Theory, Models, and Algorithms
• The Optimal Control of Partially Observable Markov Processes over the Infinite Horizon: Discounted Costs
• OPTIMAL CONTROL FOR PARTIALLY OBSERVABLE MARKOV DECISION PROCESSES OVER AN INFINITE HORIZON
• Title not available (Why is that?)
• Title not available (Why is that?)
• The Optimal Control of Partially Observable Markov Processes over a Finite Horizon
• Solution Procedures for Partially Observed Markov Decision Processes
• Title not available (Why is that?)
• Application of Jensen's inequality to adaptive suboptimal design
• A survey of solution techniques for the partially observed Markov decision process

Cited In (only showing first 100 items - show all)

• Title not available (Why is that?)
• Title not available (Why is that?)
• Performance prediction of an unmanned airborne vehicle multi-agent system
• Randomized belief-space replanning in partially-observable continuous spaces
• Using machine learning for decreasing state uncertainty in planning
• Optimal cost almost-sure reachability in POMDPs
• Partially observable game-theoretic agent programming in Golog
• Learning and planning in partially observable environments without prior domain knowledge
• Recursively modeling other agents for decision making: a research perspective
• Reasoning about uncertain parameters and agent behaviors through encoded experiences and belief planning
• Representations for robot knowledge in the \textsc{KnowRob} framework
• Bounded-parameter partially observable Markov decision processes: framework and algorithm
• An evidential approach to SLAM, path planning, and active exploration
• Probabilistic may/must testing: retaining probabilities by restricted schedulers
• Strong planning under partial observability
• Goal-directed learning of features and forward models
• Strong planning under uncertainty in domains with numerous but identical elements (a generic approach)
• Transfer in variable-reward hierarchical reinforcement learning
• Recognizing and learning models of social exchange strategies for the regulation of social interactions in open agent societies
• Open problems in universal induction \& intelligence
• Optimal decision rules in repeated games where players infer an opponent's mind via simplified belief calculation
• The value of information for populations in varying environments
• Optimal speech motor control and token-to-token variability: a Bayesian modeling approach
• Active inference and agency: optimal control without cost functions
• Stochastic dynamic programming with factored representations
• Integrated common sense learning and planning in POMDPs
• Exact decomposition approaches for Markov decision processes: a survey
• Task-structured probabilistic I/O automata
• Exploiting symmetries for single- and multi-agent partially observable stochastic domains
• Probabilistic Reasoning by SAT Solvers
• Bottom-up learning of hierarchical models in a class of deterministic pomdp environments
• Policy iteration for bounded-parameter POMDPs
• A two-state partially observable Markov decision process with three actions
• State observation accuracy and finite-memory policy performance
• Conformant plans and beyond: principles and complexity
• A synthesis of automated planning and reinforcement learning for efficient, robust decision-making
• Solving for Best Responses and Equilibria in Extensive-Form Games with Reinforcement Learning Methods
• POMDPs under probabilistic semantics
• Partially observable Markov decision processes with imprecise parameters
• Abstraction and approximate decision-theoretic planning.
• Markov limid processes for representing and solving renewal problems
• Dynamic multiagent probabilistic inference
• Title not available (Why is that?)
• Title not available (Why is that?)
• pomdpSolve
• Group sparse optimization for learning predictive state representations
• An affective mobile robot educator with a full-time job
• Title not available (Why is that?)
• Title not available (Why is that?)
• A Bayesian approach for learning and planning in partially observable Markov decision processes
• Computing rank dependent utility in graphical models for sequential decision problems
• The Concept of Opposition and Its Use in Q-Learning and Q(λ) Techniques
• Planning for multiple measurement channels in a continuous-state POMDP
• Planning in partially-observable switching-mode continuous domains
• From knowledge-based programs to graded belief-based programs. I: On-line reasoning
• Planning in hybrid relational MDPs
• Fast strong planning for fully observable nondeterministic planning problems
• Decentralized MDPs with sparse interactions
• Reward Maximization Through Discrete Active Inference
• Title not available (Why is that?)
• Autonomous agents modelling other agents: a comprehensive survey and open problems
• Contingent planning under uncertainty via stochastic satisfiability
• Computer science and decision theory
• Multi-stage classifier design
• Testing probabilistic equivalence through reinforcement learning
• Partially observable Markov decision process approximations for adaptive sensing
• A tutorial on partially observable Markov decision processes
• DESPOT: online POMDP planning with regularization
• Partial-order planning with concurrent interacting actions
• Systems of Bounded Rational Agents with Information-Theoretic Constraints
• Cost-sensitive feature acquisition and classification
• Probabilistic reasoning about epistemic action narratives
• Counterexample-guided inductive synthesis for probabilistic systems
• A dynamic epistemic framework for reasoning about conformant probabilistic plans
• Enforcing almost-sure reachability in POMDPs
• Approximability and efficient algorithms for constrained fixed-horizon POMDPs with durative actions
• Permissive planning: Extending classical planning to uncertain task domains.
• Computation of weighted sums of rewards for concurrent MDPs
• A reinforcement learning scheme for a partially-observable multi-agent game
• Robust almost-sure reachability in multi-environment MDPs
• Integration of AI and OR Techniques in Constraint Programming for Combinatorial Optimization Problems
• Multi-goal motion planning using traveling salesman problem in belief space
• Analyzing generalized planning under nondeterminism
• Finite-horizon LQR controller for partially-observed Boolean dynamical systems
• An integrated approach to solving influence diagrams and finite-horizon partially observable decision processes
• A reinforcement learning scheme for a partially-observable multi-agent game
• Quantitative controller synthesis for consumption Markov decision processes
• Computer Vision - ECCV 2004
• Tutorial series on brain-inspired computing. IV: Reinforcement learning: machine learning and natural learning
• Myopic bounds for optimal policy of POMDPs: an extension of lovejoy's structural results
• POMDP planning for robust robot control
• Markov decision processes with sequential sensor measurements
• Title not available (Why is that?)
• Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs
• A sufficient statistic for influence in structured multiagent environments
• Representation and Timing in Theories of the Dopamine System
• A survey of inverse reinforcement learning: challenges, methods and progress
• Integration of reinforcement learning and optimal decision-making theories of the basal ganglia
• Induction and exploitation of subgoal automata for reinforcement learning
• Gradient-descent for randomized controllers under partial observability

Uses Software

• POMDPS
• Graphplan
• UCPOP

This page was built for publication: Planning and acting in partially observable stochastic domains

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q72343)