Mo' States Mo' Problems: Emergency Stop Mechanisms from Observation
By Samuel K. Ainsworth, Matt Barnes, Siddhartha S. Srinivasa. 2019
7 citations recorded by the source corpus.
In many environments, only a relatively small subset of the complete state space is necessary in order to accomplish a given task. We develop a simple technique using emergency stops (e-stops) to exploit this phenomenon. Using e-stops significantly improves sample complexity by reducing the amount of required exploration, while retaining a performance bound that efficiently trades off the rate of convergence with a small asymptotic sub-optimality gap. We analyze the regret behavior of e-stops and present empirical results in discrete and continuous settings demonstrating that our reset mechanism can provide order-of-magnitude speedups on top of existing reinforcement learning methods.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Rahul Kidambi
- Sergey Levine
- Aravind Rajeswaran
- Praneeth Netrapalli
- Yoshua Bengio
- Chelsea Finn
- Pieter Abbeel
- Ruslan Salakhutdinov
Citations in the corpus
- MOReL : Model-Based Offline Reinforcement Learning (2020, background): “Similar ideas have been explored in related settings like online RL [58, 59] and imitation learning [60].”