Planning from Pixels in Environments with Combinatorially Hard Search Spaces
The ability to form complex plans based on raw visual input is a litmus test for current capabilities of artificial intelligence, as it requires a seamless combination of visual processing and abstract algorithmic execution, two traditionally separate areas of computer science. A recent surge of interest in this field brought advances that yield good performance in tasks ranging from arcade games to continuous control; these methods however do not come without significant issues, such as limited generalization capabilities and difficulties when dealing with combinatorially hard planning instances. Our contribution is two-fold: (i) we present a method that learns to represent its environment as a latent graph and leverages state reidentification to reduce the complexity of finding a good policy from exponential to linear (ii) we introduce a set of lightweight environments with an underlying discrete combinatorial structure in which planning is challenging even for humans. Moreover, we show that our methods achieves strong empirical generalization to variations in the environment, even across highly disadvantaged regimes, such as "one-shot" planning, or in an offline RL paradigm which only provides low-quality trajectories.
Code (2)
Tasks
continuous-controlContinuous ControlOffline RLMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Bayesian Active Edge Evaluation on Expensive Graphs
Robots operate in environments with varying implicit structure. For instance, a helicopter flying over terrain encounters a very different arrangement of obstacles than a robotic arm manipulating objects on a cluttered t…
Active LearningMotion PlanningvalidForecaster: Towards Temporally Abstract Tree-Search Planning from Pixels
The ability to plan at many different levels of abstraction enables agents to envision the long-term repercussions of their decisions and thus enables sample-efficient learning. This becomes particularly beneficial in co…
Hierarchical Reinforcement LearningFrom Pixels to Shelf: An Integrated Robotic System for Autonomous Supermarket Stocking with a Mobile Manipulator
Autonomous stocking in retail environments, particularly supermarkets, presents challenges due to dynamic human interactions, constrained spaces, and diverse product geometries. This paper introduces an efficient modular…
Object DetectionChallenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks
Deep reinforcement learning has shown promise in discrete domains requiring complex reasoning, including games such as Chess, Go, and Hanabi. However, this type of reasoning is less often observed in long-horizon, contin…
Deep Reinforcement LearningGNN-DIP: Neural Corridor Selection for Decomposition-Based Motion Planning
Motion planning through narrow passages remains a core challenge: sampling-based planners rarely place samples inside these narrow but critical regions, and even when samples land inside a passage, the straight-line conn…
Graph Neural NetworkMotion Planning