Evaluating task-agnostic exploration for fixed-batch learning of arbitrary future tasks

November 20, 2019 Β· Entered Twilight Β· πŸ› arXiv.org

πŸŒ… TWILIGHT: Old Age
Predates the code-sharing era β€” a pioneer of its time

"Last commit was 6.0 years ago (β‰₯5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, LICENSE, README.md, agent.py, envs.png, params, run, session.py, task.py

Authors Vibhavari Dasagi, Robert Lee, Jake Bruce, JΓΌrgen Leitner arXiv ID 1911.08666 Category cs.LG: Machine Learning Cross-listed cs.RO, stat.ML Citations 2 Venue arXiv.org Repository https://github.com/qutrobotlearning/batchlearning Last Checked 2 months ago
Abstract
Deep reinforcement learning has been shown to solve challenging tasks where large amounts of training experience is available, usually obtained online while learning the task. Robotics is a significant potential application domain for many of these algorithms, but generating robot experience in the real world is expensive, especially when each task requires a lengthy online training procedure. Off-policy algorithms can in principle learn arbitrary tasks from a diverse enough fixed dataset. In this work, we evaluate popular exploration methods by generating robotics datasets for the purpose of learning to solve tasks completely offline without any further interaction in the real world. We present results on three popular continuous control tasks in simulation, as well as continuous control of a high-dimensional real robot arm. Code documenting all algorithms, experiments, and hyper-parameters is available at https://github.com/qutrobotlearning/batchlearning.
Community shame:
Not yet rated
Community Contributions

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

πŸ“œ Similar Papers

In the same crypt β€” Machine Learning