6 papers
Reinforcement Learning for Long-Horizon Unordered Tasks: From Boolean to Coupled Reward Machines
Kristina Levina, Nikolaos Pappas, Athanasios Karapantelakis +2
Reward machines (RMs) inform reinforcement learning agents about the reward structure of the environment, enabling support for non-Markovian tasks and improving sample efficiency.…
LLM-Evolved Domain-Independent Heuristics for Symbolic AI Planning
Elliot Gestrin, Jendrik Seipp
Heuristic search is the dominant paradigm in symbolic AI planning, and the strongest heuristics are the result of decades of work by planning researchers. Recent work has shown tha…
LLM-Evolved Pattern Generators for Optimal Classical Planning
Windy Phung, Dominik Drexler, Arnaud Lequen +1
Learned heuristics have recently become a competitive alternative to traditional domain-independent heuristics for satisficing planning. Existing approaches, however, focus on impr…
Property-Guided LLM Program Synthesis for Planning
André G. Pereira, Augusto B. Corrêa, Jendrik Seipp
LLMs have shown impressive success in program synthesis, discovering programs that surpass prior solutions. However, these approaches rely on simple numeric scores to signal progra…
Parallel Lifted Planning via Semi-Naive Datalog Evaluation
Dominik Drexler, Oliver Joergensen, Jendrik Seipp
Lifted classical planners operate directly on first-order planning tasks to avoid the computationally demanding grounding step. However, lifted planning is typically slower, as pla…
Dynamic Tree Databases in Automated Planning
Oliver Joergensen, Dominik Drexler, Jendrik Seipp
A central challenge in scaling up explicit state-space search for large tasks is compactly representing the set of generated states. Tree databases, a data structure from model che…