A Bayesian-Symbolic Approach to Reasoning and Learning in Intuitive Physics
Humans can reason about intuitive physics in fully or partially observed environments even after being exposed to a very limited set of observations. This sample-efficient intuitive physical reasoning is considered a core domain of human common sense knowledge. One hypothesis to explain this remarkable capacity, posits that humans quickly learn approximations to the laws of physics that govern the dynamics of the environment. In this paper, we propose a Bayesian-symbolic framework (BSP) for physical reasoning and learning that is close to human-level sample-efficiency and accuracy. In BSP, the environment is represented by a top-down generative model of entities, which are assumed to interact with each other under unknown force laws over their latent and observed properties. BSP models each of these entities as random variables, and uses Bayesian inference to estimate their unknown properties. For learning the unknown forces, BSP leverages symbolic regression on a novel grammar of Newtonian physics in a bilevel optimization setup. These inference and regression steps are performed in an iterative manner using expectation-maximization, allowing BSP to simultaneously learn force laws while maintaining uncertainty over entity properties. We show that BSP is more sample-efficient compared to neural alternatives on controlled synthetic datasets, demonstrate BSP's applicability to real-world common sense scenes and study BSP's performance on tasks previously used to study human physical reasoning.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian InferenceBilevel OptimizationCommon Sense ReasoningregressionSymbolic RegressionSimilar Papers 제목 키워드 기반
A Bayesian-Symbolic Approach to Learning and Reasoning for Intuitive Physics
Humans are capable of reasoning about physical phenomena by inferring laws of physics from a very limited set of observations. The inferred laws can potentially depend on unobserved properties, such as mass, texture, cha…
Bayesian InferenceCommon Sense ReasoningregressionSymbolic RegressionNeural spatio-temporal reasoning with object-centric self-supervised learning
Transformer-based language models have proved capable of rudimentary symbolic reasoning, underlining the effectiveness of applying self-attention computations to sets of discrete entities. In this work, we apply this le…
Language ModellingSelf-Supervised LearningBayesian Inverse Physics for Neuro-Symbolic Robot Learning
Real-world robotic applications, from autonomous exploration to assistive technologies, require adaptive, interpretable, and data-efficient learning paradigms. While deep learning architectures and foundation models have…
Bayesian InferenceDecision MakingMeta-LearningAdding Intuitive Physics to Neural-Symbolic Capsules Using Interaction Networks
Many current methods to learn intuitive physics are based on interaction networks and similar approaches. However, they rely on information that has proven difficult to estimate directly from image data in the past. We a…
A Neural-Symbolic Framework for Mental Simulation
We present a neural-symbolic framework for observing the environment and continuously learning visual semantics and intuitive physics to reproduce them in an interactive simulation. The framework consists of five parts, …
Meta-Learning