Probing Emergent Semantics in Predictive Agents via Question Answering
Authors: Abhishek Das, Federico Carnevale, Hamza Merzic, Laura Rimell, Rosalia Schneider, Josh Abramson, Alden Hung, Arun Ahuja, Stephen Clark, Greg Wayne, Felix Hill
ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate predictive vs. non-predictive agents (both trained for exploration) on our question-answering testbed to investigate how much knowldge of object shapes, quantities, and spatial relations they acquire solely by egocentric prediction. Concretely, we make the following contributions: |
| Researcher Affiliation | Collaboration | 1Georgia Institute of Technology 2Deep Mind. |
| Pseudocode | No | The paper describes methods and architectures in prose and diagrams, but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any explicit statements or links indicating that the source code for the described methodology is publicly available. |
| Open Datasets | No | The paper describes programmatically generating a dataset of questions within their custom Unity environment and the Deep Mind Lab environment, but does not provide explicit access information (link, DOI, repository, or formal citation for public availability) for this generated dataset. |
| Dataset Splits | No | The paper mentions 'disjoint train and test splits' for compositional generalization testing, but it does not specify explicit percentages, sample counts, or detailed methodology for dataset partitioning for overall training, validation, or testing. |
| Hardware Specification | No | The paper does not explicitly describe the specific hardware (e.g., GPU, CPU models, or memory) used for running its experiments. |
| Software Dependencies | No | The paper mentions frameworks and models used (e.g., Unity, IMPALA, ResNet, Conv DRAW, GECO, CPC|A, Sim Core) but does not provide specific version numbers for any ancillary software dependencies or libraries. |
| Experiment Setup | Yes | The hyper-parameter values used in all the experiments are in Table 3. |