Decomposition Techniques for Planning in Stochastic Domains

By Thomas L. Dean, Shieu-Hong Lin. 1995

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Graying the black box: Understanding DQNs (2016, background): “Given a good representation of the states, varying levels of convergence guarantees has been promised (Dean & Lin, 1995; Parr, 1998; Hauskrecht et al., 1998; Dietterich, 2000).”
Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition (1999, methodology): “It is interesting that the iterative method described by Dean and Lin (1995) can be viewed as a method for moving along this tradeoff.”
Hierarchical Solution of Markov Decision Processes using Macro-actions (1998, background): “After some ﬁnite number n of iterations, the choice of maximizing action for each s forms an optimal policy (cid:25) and V n approximates its value.”
Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning (1999, background): “On the other hand, temporal abstraction can be introduced into reinforcement learning in a variety of ways [33–61].”
Planning, Learning and Coordination in Multiagent Decision Processes (1996, methodology): “These aggregates are treated as a single state in dynamic programming algorithms for the solutionof MDPs or the related methods used in RL [44, 5, 36, 7, 9, 19, 22, 14, 38].”
Visualizing Dynamics: from t-SNE to SEMI-MDPs (2016, methodology): “Good temporal representation of the data can speed up the prerformence of Reinforcement Learning (RL) algorithms (Dietterich, 2000; Dean & Lin, 1995; Parr, 1998; Hauskrecht et al., 1998), and indeed there is a growing interest in developing hierarchical DRL algorithms.”
Reinforcement Learning with Hierarchies of Machines (1997, methodology): “Moreover, the HAM structure provides a natural decomposition of the HAM-induced model, making it amenable to the divide-and-conquer approaches of [8] and [2].”
Discovering Hierarchy in Reinforcement Learning with HEXQ (2002, unknown): “Many researchers have either ignored where decompositions come from or pointed to the desirability of automating this task (Boutilier et al., 1999; Hauskrecht et al., 1998; Dean & Lin, 1995).”
Autonomous discovery of temporal abstractions from interaction with an environment (2002, methodology): “The MAXQ algorithm by Dietterich (1998) provides an alternate framework for temporal abstraction in RL. His system uses a fixed hierarchy of temporal abstractions, where each action at each level of the hierarchy has a separate value function. Each level of the hierarchy also has a value function to”
Tree Based Discretization for Continuous State Space Reinforcement Learning (1998, methodology): “Gordon (1995) showed how to use an averaging system to sub-sample the state space.”