Scoring-Aggregating-Planning: Learning task-agnostic priors from interactions and sparse rewards for zero-shot generalization
Humans can learn task-agnostic priors from interactive experience and utilize the priors for novel tasks without any finetuning. In this paper, we propose Scoring-Aggregating-Planning (SAP), a framework that can learn task-agnostic semantics and dynamics priors from arbitrary quality interactions as well as the corresponding sparse rewards and then plan on unseen tasks in zero-shot condition. The framework finds a neural score function for local regional state and action pairs that can be aggregated to approximate the quality of a full trajectory; moreover, a dynamics model that is learned with self-supervision can be incorporated for planning. Many of previous works that leverage interactive data for policy learning either need massive on-policy environmental interactions or assume access to expert data while we can achieve a similar goal with pure off-policy imperfect data. Instantiating our framework results in a generalizable policy to unseen tasks. Experiments demonstrate that the proposed method can outperform baseline methods on a wide range of applications including gridworld, robotics tasks and video games.
Code (0)
등록된 구현이 없습니다.
Tasks
Zero-shot GeneralizationSimilar Papers 제목 키워드 기반
Scoring-Aggregating-Planning: Learning task-agnostic priors from interactions and sparse rewards for zero-shot generalization
Abstract Humans can learn task-agnostic priors from interactive experience and utilize the priors for novel tasks without any finetuning. In this paper, we propose Scoring-Aggregating-Planning (SAP), a framework that ca…
Zero-shot GeneralizationPsychiatryBench: A Multi-Task Benchmark for LLMs in Psychiatry
Large language models (LLMs) offer significant potential in enhancing psychiatric practice, from improving diagnostic accuracy to streamlining clinical documentation and therapeutic support. However, existing evaluation …
More Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models
Vision-Language Model (VLM) driving agents promise explainable end-to-end autonomy by first producing natural-language reasoning and then predicting trajectory planning. However, whether planning is causally driven by th…
Visual Question AnsweringTrajectory PlanningRecognizing Object Affordances to Support Scene Reasoning for Manipulation Tasks
Affordance information about a scene provides important clues as to what actions may be executed in pursuit of meeting a specified goal state. Thus, integrating affordance-based reasoning into symbolic action plannning p…
Affordance DetectionAffordance RecognitionBenchmarkingObject+2Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation
In robotic manipulation, the tight coupling between grasping and motion planning often obscures the true source of failure, leading to inefficient trial-and-error. To enable efficient long-horizon manipulation, we propos…
Motion Planning