6 papers
Structure-Induced Information for Rerooting Levin Tree Search
Jake Tuero, Michael Buro, Laurent Orseau +1
Subgoal-based policy tree search, which uses a policy to guide search, is effective for complex single-agent deterministic problems but often relies on explicit subgoal generation…
Gradient-Based Program Synthesis with Neurally Interpreted Languages
Matthew V. Macfarlane, Clément Bonnet, Herke van Hoof +1
A central challenge in program induction has long been the trade-off between symbolic and neural approaches. Symbolic methods offer compositional generalisation and data efficiency…
Subgoal-Guided Policy Heuristic Search with Learned Subgoals
Jake Tuero, Michael Buro, Levi H. S. Lelis
Policy tree search is a family of tree search algorithms that use a policy to guide the search. These algorithms provide guarantees on the number of expansions required to solve a…
Common Benchmarks Undervalue the Generalization Power of Programmatic Policies
Amirhossein Rajabpour, Kiarash Aghakasiri, Sandra Zilles +1
Algorithms for learning programmatic representations for sequential decision-making problems are often evaluated on out-of-distribution (OOD) problems, with the common conclusion t…
InnateCoder: Learning Programmatic Options with Foundation Models
Rubens O. Moraes, Quazi Asif Sadmine, Hendrik Baier +1
Outside of transfer learning settings, reinforcement learning agents start their learning process from a clean slate. As a result, such agents have to go through a slow process to…
Exponential Speedups by Rerooting Levin Tree Search
Laurent Orseau, Marcus Hutter, Levi H. S. Lelis
Levin Tree Search (LTS) (Orseau et al., 2018) is a search algorithm for deterministic environments that uses a user-specified policy to guide the search. It comes with a formal gua…