Labeled RTDP: Improving the Convergence of Real-Time Dynamic Programming

By Blai Bonet, Hector Geffner. International Conference on Automated Planning and Scheduling, 2003

388 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/5d06c6746f1d3cf0db3d78b21befe40b0dc8586c

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

An Algorithm Better than AO*? (2005, unknown): “The results for Min-Max LRTA* show that its performance is similar toLDFS but inferior to BoundedLDFS except inRULES.”
Online Planning for Large Markov Decision Processes with Hierarchical Decomposition (2015, methodology): “RELATED WORK In the context of online planning for MDPs, RTDP [Barto et al. 1995; Bonet and Geffner 2003; McMahan et al. 2005; Sanner et al. 2009] is among the ﬁrst that tries to ﬁnd a near-optimal action for the current state by conducting trial-based search process with greedy action selection…”
Automated Planning and Acting (2016, methodology): “The Find&Revise schema was proposed by Bonet and Geffner [83], who also developed several instantiation of this schema into heuristic search algorithms such as HDP [83], LRTDP [84] and LDFS [86].”
Action Schema Networks: Generalised Policies with Deep Learning (2017, methodology): “Since LRTDP and iLAO* are optimal planners, we execute them until convergence ( (cid:15) =10 − 4 ) for each problem us-ing 30 different random seeds.”
Reinforcement Learning and Markov Decision Processes (2012, methodology): “Markov Decision Processes (MDP) Puterman (1994) are an intuitive and fundamental formalism for decision-theoretic planning (DTP) Boutilier et al (1999); Boutilier (1999), reinforcement learning (RL) Bertsekas and Tsitsiklis (1996); Sutton and Barto (1998); Kaelbling et al (1996) and other learning p”
Plan Recognition as Planning (2009, methodology): “16 (Vmin Heuristic (Bonet and Geffner, 2003)).”