Improving Long-Horizon Imitation through Instruction Prediction
Authors: Joey Hejna, Pieter Abbeel, Lerrel Pinto
AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section we detail our experimental setup and empirical results. In particular, we investigate the benefits of instruction modeling for planning in limited data regimes. |
| Researcher Affiliation | Academia | Joey Hejna1, Pieter Abbeel2, Lerrel Pinto3 1 Stanford University 2 University of California, Berkeley 3 New York University jhejna@cs.stanford.edu, pabbeel@berkeley.edu, lerrel@cs.nyu.edu |
| Pseudocode | No | The paper includes architectural diagrams (Figure 1, Appendix C) but no explicitly labeled "Pseudocode" or "Algorithm" blocks. |
| Open Source Code | Yes | More details and code can be found at https://github.com/jhejna/instruction-prediction. |
| Open Datasets | Yes | To evaluate the effectiveness of instruction prediction at enabling long-horizon planning and generalization, we test our method on Baby AI (Chevalier-Boisvert et al. 2019) and the Crafting Environment from Chen, Gupta, and Marino (2021) which both provide coarse instructions. |
| Dataset Splits | No | The paper describes using portions of benchmark datasets for training and evaluating on 'unseen tasks' but does not explicitly provide percentages or counts for training, validation, and test splits, nor does it mention a dedicated validation set. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running the experiments, such as GPU or CPU models, or memory specifications. |
| Software Dependencies | No | The paper mentions software components like transformer networks and PyTorch (implied by typical deep learning setups), but it does not specify version numbers for these or any other software dependencies. |
| Experiment Setup | No | The paper states 'Full model hyperparameters can be found in the Appendix' but does not provide specific hyperparameter values or training configurations within the main body of the text. |