Memory-Based Reinforcement Learning: Efficient Computation with Prioritized Sweeping

By Andrew W. Moore, Christopher G. Atkeson. 1992

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

Self-Imitation Learning (2018, background): “Prioritized experience replay (Moore & Atkeson, 1992; Schaul et al., 2016) proposed an efﬁcient way of learning from past experiences by prioritizing them based on temporal-difference error.”
Feudal Reinforcement Learning (1992, background): “3-(2,1) 3-(2,2) 3-(2,3) 3-(2,4) 3-(2,5) 3-(2,6) 3-(2,7) 3-(2,8)”
Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization (2021, unknown): “Early work on Model-based RL uses simple tabular (Sutton, 1990; Moore and Atkeson, 1993; Peng and Williams, 1993) and locally linear (Atkeson et al.”
Structure-Adaptable Digital Neural Networks (1999, methodology): “A number of new algorithms exploiting this idea and optimizing the use of the internal model of the world have been proposed [11, 142, 151], but we have not analyzed if they are suitable for a digital implementation.”
Learning to Use Selective Attention and Short-Term Memory in Sequential Tasks (1996, background): “3If computational limitations or the number of states makes full value iteration too expensive, we can instead do Prioritized Sweeping [Moore and Atkeson, 1993], Q-DYNA [Peng and Williams, 1992] or even Q-learning [Watkins, 1989].”
Learning to Act Using Real-Time Dynamic Programming (1995, background): “Similarly, using the kd-tree data structure to access state costs, as explored by Moore [55,56], can provide efficient storage and retrieval of the costs of a finite set of states from a k-dimensional state space.”
Efficient Learning and Planning Within the Dyna Framework (1993, methodology): “…providing external information that is relevant in many parts of the state orstate-action space.2An additional aspect considered in some depth by Moore and Atkeson (1992) in their2For example, suppose we tell the agent traversing the maze of Figure 6 at some point that any stepin a southward…”