AUTOMATED DISCOVERY OF OPTIONS IN REINFORCEMENT LEARNING

2003

Citations in the corpus

• Graying the black box: Understanding DQNs (2016, methodology): “In this work we analyze the representation of states learned by DRL agents.”
• Skill Characterization Based on Betweenness (2008, background): “Stolle & Precup [4] and Stolle [5] address this last concern by obtaining their trajectories from multiple tasks that start and terminate at different states.”
• Online Planning for Large Markov Decision Processes with Hierarchical Decomposition (2015, methodology): “…by applying DBN models to successful execution trajectories MDPs by finding nested sub-MDPs where there are policies to reach any exit with certainty; and Stolle [2004] performs automatic hierarchical decomposition by taking advantage of the factored representation of the underlying problem.”
• Learning From Observation and Practice Using Behavioral Primitives : Marble Maze (2004, background): “[18] and [4] review recent approaches to the use of primitives in reinforcement learning.”
• Multi-Level Discovery of Deep Options (2017, background): “Naively, the number of different contexts that the d highest levels can provide to lower levels grows exponentially with d .”