Related papers: Subgoal Search For Complex Reasoning Tasks
We consider a set of challenging sequential manipulation puzzles, where an agent has to interact with multiple movable objects and navigate narrow passages. Such settings are notoriously difficult for Task-and-Motion Planners, as they…
In this work we propose a planning and acting architecture endowed with a module which learns to select subgoals with Deep Q-Learning. This allows us to decrease the load of a planner when faced with scenarios with real-time restrictions.…
Learning to solve complex goal-oriented tasks with sparse terminal-only rewards often requires an enormous number of samples. In such cases, using a set of expert trajectories could help to learn faster. However, Imitation Learning (IL) via…
Rubik's Cube is an easily-understood puzzle, which is originally called the "magic cube". It is a well-known planning problem, which has been studied for a long time. Yet many simple properties remain unknown. This paper studies whether…
Most human behaviors consist of multiple parts, steps, or subtasks. These structures guide our action planning and execution, but when we observe others, the latent structure of their actions is typically unobservable, and must be inferred…
The ability to plan actions on multiple levels of abstraction enables intelligent agents to solve complex tasks effectively. However, learning the models for both low and high-level planning from demonstrations has proven challenging,…
A $k$-submodular function naturally generalizes submodular functions by taking as input $k$ disjoint subsets, rather than a single subset. Unlike standard submodular maximization, which only requires selecting elements for the solution,…
Similar trajectory search is a fundamental problem and has been well studied over the past two decades. However, the similar subtrajectory search (SimSub) problem, aiming to return a portion of a trajectory (i.e., a subtrajectory) which is…
Large Language Models (LLMs) have driven substantial progress in artificial intelligence in recent years, exhibiting impressive capabilities across a wide range of tasks, including mathematical problem-solving. Inspired by the success of…
Planning is hard. The use of subgoals can make planning more tractable, but selecting these subgoals is computationally costly. What algorithms might enable us to reap the benefits of planning using subgoals while minimizing the…
Recently, reinforcement learning has been successfully applied to the logical game of Go, various Atari games, and even a 3D game, Labyrinth, though it continues to have problems in sparse reward settings. It is difficult to explore, but…
Many AI problems, in robotics and other domains, are goal-directed, essentially seeking a trajectory leading to some goal state. In such problems, the way we choose to represent a trajectory underlies algorithms for trajectory prediction…
Reinforcement learning in sparse-reward navigation environments with expensive and limited interactions is challenging and poses a need for effective exploration. Motivated by complex navigation tasks that require real-world training (when…
Since its first appearance, transformers have been successfully used in wide ranging domains from computer vision to natural language processing. Application of transformers in Reinforcement Learning by reformulating it as a sequence…
Many puzzle video games, like Sokoban, involve moving some agent in a maze. The reachable locations are usually apparent for a human player, and the difficulty of the game is mainly related to performing actions on objects, such as pushing…
Multi-step reasoning remains a central challenge for large language models: single-pass generation is efficient but lacks accuracy; tree-search methods explore multiple paths but are computation-heavy. We address this gap by distilling…
Developing agents to engage in complex goal-oriented dialogues is challenging partly because the main learning signals are very sparse in long conversations. In this paper, we propose a divide-and-conquer approach that discovers and…
While Transformers have enabled tremendous progress in various application settings, such architectures still trail behind traditional symbolic planners for solving complex decision making tasks. In this work, we demonstrate how to train…
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 given problem that are based on the quality of the policy.…
Path planning in a changing environment is a challenging task in robotics, as moving objects impose time-dependent constraints. Recent planning methods primarily focus on the spatial aspects, lacking the capability to directly incorporate…