See, Hear, Explore: Curiosity via Audio-Visual Association

July 07, 2020 ยท Entered Twilight ยท ๐Ÿ› Neural Information Processing Systems

๐ŸŒ… TWILIGHT: Old Age
Predates the code-sharing era โ€” a pioneer of its time

"No code URL or promise found in abstract"
"Derived repo from GitHub Pages (backfill)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, README.md, __init__.py, auxiliary_tasks.py, cnn_policy.py, cppo_agent.py, environment.yml, intrinsic_model.py, make_plots.py, mpi_utils.py, recorder.py, retro_env.py, rollouts.py, run.py, utils.py, vec_env.py, wrappers.py

Authors Victoria Dean, Shubham Tulsiani, Abhinav Gupta arXiv ID 2007.03669 Category cs.LG: Machine Learning Cross-listed cs.AI, cs.CV, stat.ML Citations 64 Venue Neural Information Processing Systems Repository https://github.com/vdean/audio-curiosity.html. โญ 23 Last Checked 8 days ago
Abstract
Exploration is one of the core challenges in reinforcement learning. A common formulation of curiosity-driven exploration uses the difference between the real future and the future predicted by a learned model. However, predicting the future is an inherently difficult task which can be ill-posed in the face of stochasticity. In this paper, we introduce an alternative form of curiosity that rewards novel associations between different senses. Our approach exploits multiple modalities to provide a stronger signal for more efficient exploration. Our method is inspired by the fact that, for humans, both sight and sound play a critical role in exploration. We present results on several Atari environments and Habitat (a photorealistic navigation simulator), showing the benefits of using an audio-visual association model for intrinsically guiding learning agents in the absence of external rewards. For videos and code, see https://vdean.github.io/audio-curiosity.html.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning