Size Independent Neural Transfer for RDDL Planning
ICAPS, pp. 631-636, 2019.
Neural planners for RDDL MDPs produce deep reactive policies in an offline fashion. These scale well with large domains, but are sample inefficient and time-consuming to train from scratch for each new problem. To mitigate this, recent work has studied neural transfer learning, so that a generic planner trained on other problems of the sa...More
PPT (Upload PPT)