Learning to act using real-time dynamic programming

1995/01/01 by Andrew G. Barto, Steven J. Bradtke, Satinder Singh +1 · 1,113 citations
Computer Science · #AI-based Problem Solving and Planning #Algorithm #Artificial intelligence #Asynchronous communication #Bridge (graph theory) #Computer science #Control (management) #Dynamic programming #Evolutionary Algorithms and Applications #Machine learning #Reinforcement Learning in Robotics #Reinforcement learning #Temporal difference learning

paper · pdf · doi:10.1016/0004-3702(94)00011-o

published in Artificial Intelligence 72(1-2), 81-138 (Elsevier BV)

openalex publication_date 1995/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/03

Citations

• Real-time heuristic search

Cited by

• Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
• Deliberation for autonomous robots: A survey
• Robot shaping: developing autonomous agents through learning
• Stochastic Reset Pathfinding: Path-Level Regret for Cascading Bandits over Graph Paths
• Bayesian Reinforcement Learning via Deep, Sparse Sampling
• Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control
• Maximizing Cumulative User Engagement in Sequential Recommendation: An Online Optimization Perspective
• Learning under Invariable Bayesian Safety
• Multi-Objective Statistical Model Checking using Lightweight Strategy Sampling (extended version)
• Minimizing the Negative Side Effects of Planning with Reduced Models
• Focused Model-Learning and Planning for Non-Gaussian Continuous State-Action Systems
• On the Complexity of Solving Markov Decision Problems
• Zero-Shot Reinforcement Learning with Deep Attention Convolutional Neural Networks
• Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies
• Searching for Plannable Domains can Speed up Reinforcement Learning
• Modeling and Analysis of Energy Harvesting and Smart Grid-Powered Wireless Communication Networks: A Contemporary Survey
• Anytime State-Based Solution Methods for Decision Processes with non-Markovian Rewards
• Online Planning with Lookahead Policies
• Value Iteration in Continuous Actions, States and Time
• Suboptimality Bounds for Stochastic Shortest Path Problems
• Metareasoning for Planning Under Uncertainty
• An Approximate Solution Method for Large Risk-Averse Markov Decision Processes
• A Programming Language With a POMDP Inside
• A novel approach to model exploration for value function learning
• Tracking the Race Between Deep Reinforcement Learning and Imitation Learning -- Extended Version
• Action Selection for MDPs: Anytime AO* vs. UCT
• From self-tuning regulators to reinforcement learning and back again
• Learning for Adaptive Real-time Search
• Mean-based Heuristic Search for Real-Time Planning
• Scaling Up Decentralized MDPs Through Heuristic Search
• Cost Based Satisficing Search Considered Harmful
• Stochastic Shortest Path with Energy Constraints in POMDPs
• On Exact Solutions to the Linear Bellman Equation
• Uncertain Machine Ethics Planning
• Symbolic Generalization for On-line Planning
• Kernel-Based Reinforcement Learning: A Finite-Time Analysis
• On Backtracking in Real-time Heuristic Search
• On the Reduction of Variance and Overestimation of Deep Q-Learning
• Multi-armed Bandit for Stochastic Shortest Path in Mixed Autonomy
• \cal Q \cal D-Learning: A Collaborative Distributed Strategy for Multi-Agent Reinforcement Learning Through \rm Consensus + \rm Innovations
• A Finite-State Controller Based Offline Solver for Deterministic POMDPs
• Solving Markov Decision Processes with Reachability Characterization from Mean First Passage Times
• Decision-Theoretic Planning: Structural Assumptions and Computational Leverage
• Reinforcement Learning and Markov Decision Processes
• Fuzzy Q-learning: a new approach for fuzzy dynamic programming
• A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov Decision Processes
• Guided Policy Exploration for Markov Decision Processes Using an Uncertainty-Based Value-of-Information Criterion
• A Heuristic Search Algorithm for Solving First-Order MDPs
• Reactive Reinforcement Learning in Asynchronous Environments. [europepmc]
• A Unifying Framework for Reinforcement Learning and Planning. [europepmc]
• A Dynamic Programming Algorithm for Finding an Optimal Sequence of Informative Measurements. [europepmc]
• Deep Statistical Model Checking [europepmc]
• Momba: JANI Meets Python [europepmc]