1 Stanford University, USA, 2 University of Cambridge, UK
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 effects in the environment. For these type of tasks, we propose Causal-PIK, a method that leverages Bayesian Optimization to reason about causal interactions via a Physics-Informed Kernel to help guide efficient search for the best next action. Experimental results on Virtual Tools and PHYRE physical reasoning benchmarks show that Causal-PIK outperforms state-of-the-art results, requiring fewer actions to reach the goal. We also compare Causal-PIK to human studies, including results from a new user study we conducted on the PHYRE benchmark. We find that Causal-PIK remains competitive on tasks that are very challenging, even for human problem-solvers.
Model | AUCCESS $\,\,\uparrow$ |
---|---|
RAND | 16.0±20 |
DQN | 25.0±24.0 |
SSUP (Allen et al., 2020) | 58.0±27.0 |
Ours RBF | 42.0±33.0 |
Ours Causal-PIK | 65.0±25.0 |
Humans (Allen et al., 2020) | 53.25±23 |
Model | AUCCESS $\,\,\uparrow$ |
---|---|
Dec [Joint] (Girdhar et al., 2020)$^*$ | 40.3±8 |
MEM$^\dagger$ | 18.5±5.1 |
DQN$^\dagger$ | 36.8±9.7 |
Ahmed et al. 2021$^\dagger$ | 41.9±8.8 |
RPIN (Qi et al., 2021)$^\dagger$ | 42.2±7.1 |
RAND | 13.0±5.0 |
Harter et al. 2020 | 30.24±8.9 |
Ours RBF | 27.70±9.68 |
Ours Causal-PIK | 41.6±9.33 |
Ours Causal-PIK @10$^+$ | 24.8±9.22 |
Humans @10$^+$ | 36.6±10.2 |
We introduce Causal-PIK, a novel approach that integrates a Physics-Informed Kernel with BO to reason about causality in single-intervention physical reasoning tasks. By leveraging information from past failed attempts, our method enables agents to efficiently search for optimal actions, reducing the number of trials needed to solve tasks with complex dynamics. Our experimental results demonstrate that Causal-PIK outperforms state-of-the-art baselines, requiring fewer attempts on average to solve the puzzles from the Virtual Tools and PHYRE benchmarks.
@inproceedings{morlanscausal, title={Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel}, author={Morlans, Carlota Par{\'e}s and Yi, Michelle and Chen, Claire and Wu, Sarah A and Antonova, Rika and Gerstenberg, Tobias and Bohg, Jeannette}, booktitle={Forty-second International Conference on Machine Learning} }