Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Self-Supervised Exploration via Disagreement
Authors: Deepak Pathak, Dhiraj Gandhi, Abhinav Gupta
ICML 2019 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the efficacy of this formulation across a variety of benchmark environments including stochastic-Atari, Mujoco and Unity. Finally, we implement our differentiable exploration on a real robot which learns to interact with objects completely from scratch. |
| Researcher Affiliation | Collaboration | Deepak Pathak * 1 Dhiraj Gandhi * 2 Abhinav Gupta 2 3 1UC Berkelely 2CMU 3Facebook AI Research. |
| Pseudocode | No | No pseudocode or clearly labeled algorithm blocks were found in the paper. |
| Open Source Code | Yes | Project videos and code are at https://pathak22.github.io/exploration-by-disagreement/. |
| Open Datasets | Yes | We demonstrate the efficacy of this formulation across a variety of benchmark environments including stochastic-Atari, Mujoco and Unity. Finally, we implement our differentiable exploration on a real robot which learns to interact with objects completely from scratch. Project videos and code are at https://pathak22.github.io/exploration-by-disagreement/. |
| Dataset Splits | Yes | Out of a total of 30 objects, we created a set of 20 objects for training and 10 objects for testing. |
| Hardware Specification | No | The paper does not provide specific details on the computational hardware (e.g., GPU/CPU models, memory) used for running experiments. |
| Software Dependencies | No | The paper mentions software like PPO, Mujoco, Unity ML-agent, but does not provide specific version numbers for these or other software dependencies. |
| Experiment Setup | Yes | In particular, we use random feature space in all video games and navigation, classification features in MNIST and Image Net-pretrained Res Net-18 features in real world robot experiments. We use 5 models in the ensemble. |