The parti-game algorithm for variable resolution reinforcement learning in multidimensional state-spaces

By Andrew W. Moore, Christopher G. Atkeson. 1993

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

Deep learning in neural networks: An overview (2014, methodology): “Numerous alternative HRL techniques have been proposed (e.g., Ring, 1991, 1994; Jameson, 1991; Tenenberg et al., 1993; Moore and Atkeson, 1995; Precup et al., 1998; Dietterich, 2000b; Menache et al., 2002; Doya et al., 2002; Ghavamzadeh and Mahadevan, 2003; Barto and Mahadevan, 2003; Samejima et al.”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “Numerous alternative HRL techniques have been proposed [204, 206, 117, 279, 295, 171, 195, 50, 162, 51, 15, 215, 11, 260].”
Tree based hierarchical reinforcement learning (2002, methodology): “Moore and Atkeson (1993), to find a policy for the abstract SMDP: a function”
Formal Theory of Creativity, Fun, and Intrinsic Motivation (1990–2010) (2010, methodology): “Nonetheless, an interesting aspect of IAC's greedy reward maximizer, is that it splits the state space into regions, reminiscent of algorithms by Doya [14] and Moore [49]; this might make learning more robust in certain situations. covers some of the topics discussed in the first paper on this subje”
Reinforcement Learning on Slow Features of High-Dimensional Input Streams (2010, background): “There, the main approach is either to reduce the size of a discrete state space or to discretize a continuous state-space [59,60].”
Policy Search in a Space of Simple Closed-form Formulas: Towards Interpretability of Reinforcement Learning (2012, background): “We use the LOR, ACR, CAR and B benchmarks as defined in the appendices of [8], with the same testing initial states P 0 as them.”
From pixels to policies: A bootstrapping agent (2008, unknown): “parti-game [24], U-Trees [20], G Algorithm [25]).”
Closed-Loop Learning of Visual Control Policies (2011, unknown): “In previous work ( Moore & Atkeson, 1995; Ernst et al., 2003), the agent was always assumed to have direct access to a numerical measure of its position and velocity.”
Fast replanning for navigation in unknown terrain (2005, methodology): “Finally, versions of have been used to implement greedy mapping [14], a particular mapping method [8], and the parti-game method [15], a particular reinforcement-learning method for control [16].”
Adaptive Tile Coding for Value Function Approximation (2007, methodology): “The Parti-game algorithm (Moore & Atkeson 1995) automatically partitions state spaces but applies only to tasks with known goal regions and assumes the existence of a greedy local controller.”
D*lite (2002, methodology): “We therefore used D* Lite to implement a deterministic version of the parti-game algorithm (Moore & Atkeson 1995) with adaptive discretization that discretizes terrain into cells with nonuniform resolution.”
Variable Resolution Discretization in Optimal Control (2002, background): “For a description of the dynamics of this problem, see Moore and Atkeson (1995).”
Autonomous discovery of temporal abstractions from interaction with an environment (2002, background): “Since this dissertation does not focus on state abstraction, we will not address the work on state abstraction directly although there has been interesting work in that area (e.g., Lin, 1993a,b; Moore, 1994; McCallum, 1995; Uther, 1998).”
Gaussian Processes in Reinforcement Learning (2003, methodology): “For reasons of presentability of the value function, we below consider the well-known mountain car problem “park on the hill”, as described by Moore and Atkeson (1995) where the state-space is only two-dimensional.”
A Study of Reinforcement Learning in the Continuous Case by the Means of Viscosity Solutions (2000, methodology): “…and variable resolution discretizations (like the adaptive discretizations of (Munos & Moore, 1999; Munos, 1997c), the parti-game algorithm of (Moore & Atkeson, 1995), the multi- grid methods of (Akian, 1990) and (Pareigis, 1996), or the sparse grids of (Griebel, 1998)), the study of the…”