PHYRE: A New Benchmark for Physical Reasoning
Understanding and reasoning about physics is an important ability of intelligent agents. We develop the PHYRE benchmark for physical reasoning that contains a set of simple classical mechanics puzzles in a 2D physical environment. The benchmark is designed to encourage the development of learning algorithms that are sample-efficient and generalize well across puzzles. We test several modern learning algorithms on PHYRE and find that these algorithms fall short in solving the puzzles efficiently. We expect that PHYRE will encourage the development of novel sample-efficient agents that learn efficient but useful models of physics. For code and to play PHYRE for yourself, please visit https://player.phyre.ai.
Code (2)
Tasks
Visual ReasoningSimilar Papers 제목 키워드 기반
InPhyRe Discovers: Large Multimodal Models Struggle in Inductive Physical Reasoning
Large multimodal models (LMMs) encode physical laws observed during training, such as momentum conservation, as parametric knowledge. It allows LMMs to answer physical reasoning queries, such as the outcome of a potentia…
Visual Question AnsweringForward Prediction for Physical Reasoning
Physical reasoning requires forward prediction: the ability to forecast what will happen next given some initial world state. We study the performance of state-of-the-art forward-prediction models in the complex physical…
PredictionVisual ReasoningI-PHYRE: Interactive Physical Reasoning
Current evaluation protocols predominantly assess physical reasoning in stationary scenes, creating a gap in evaluating agents' abilities to interact with dynamic events. While contemporary methods allow agents to modify…
Zero-shot GeneralizationCausal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel
Tasks that involve complex interactions between objects with unknown dynamics make planning before execution difficult. These tasks require agents to iteratively improve their actions after actively exploring causes and …
Bayesian OptimizationPhyRPR: Training-Free Physics-Constrained Video Generation
Recent diffusion-based video generation models can synthesize visually plausible videos, yet they often struggle to satisfy physical constraints. A key reason is that most existing approaches remain single-stage: they en…
Video Generation