Planning

The Goal-Directed Frame for General Agents
Reinforcement learning is often framed around episodic, discounted, or average scalar rewards. While useful, these views miss a core …
Geraud Nangue Tasse, Steven James, Benjamin Rosman
PDF Cite
Skill-Driven Neurosymbolic State Abstractions
We consider how to construct state abstractions compatible with a given set of abstract actions, to obtain a well-formed abstract …
Alper Ahmetoglu, Steven James, Cameron Allen, Sam Lobel, David Abel, George Konidaris
PDF Cite
MinePlanner: A Benchmark for Long-Horizon Planning in Large Minecraft Worlds
We propose a new benchmark for planning tasks based on the Minecraft game. Our benchmark contains 45 tasks overall, but also provides …
William Hill, Ireton Liu, Anita De Mello Koch, Damion Harvey, Nishanth Kumar, George Konidaris, Steven James
PDF Cite
World Value Functions: Knowledge Representation for Learning and Planning
We propose world value functions (WVFs), a type of goaloriented general value function that represents how to solve not just a given …
Geraud Nangue Tasse, Benjamin Rosman, Steven James
PDF Cite
An Analysis of Monte Carlo Tree Search
Monte Carlo Tree Search (MCTS) is a family of directed search algorithms that has gained widespread attention in recent years. Despite …
Steven James, George Konidaris, Benjamin Rosman
PDF Cite
An Investigation into the Effectiveness of Heavy Rollouts in UCT
Monte Carlo Tree Search (MCTS) is a family of directed search algorithms that has gained widespread attention in recent years, with its …
Steven James, Benjamin Rosman, George Konidaris
PDF Cite