Automated curriculum generation for Policy Gradients from Demonstrations
By Anirudh Srinivasan, Dzmitry Bahdanau, Maxime Chevalier-Boisvert, Yoshua Bengio. 2019
In this paper, we present a technique that improves the process of training an agent (using RL) for instruction following. We develop a training curriculum that uses a nominal number of expert demonstrations and trains the agent in a manner that draws parallels from one of the ways in which humans learn to perform complex tasks, i.e by starting from the goal and working backwards. We test our method on the BabyAI platform and show an improvement in sample efficiency for some of its tasks compared to a PPO (proximal policy optimization) baseline.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Khimya Khetarpal
- Matthew Riemer
- Irina Rish
- Doina Precup
- Sergey Levine
- A. Mahmood
- Joelle Pineau
- Richard S. Sutton
Citations in the corpus
- Towards Continual Reinforcement Learning: A Review and Perspectives (2020, background): “, 2009; Barto, 2013; Achiam and Sastry, 2017) and learning an agent’s own curriculum (Schmidhuber, 2013; Justesen and Risi, 2018; Srinivasan et al., 2019).”