@inproceedings{zintgraf2021exploration,
author = {Zintgraf, Luisa and Feng, Leo and Lu, Cong and Igl, Maximilian and Hartikainen, Kristian and Hofmann, Katja and Whiteson, Shimon},
title = {Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning},
booktitle = {2021 International Conference on Machine Learning},
year = {2021},
month = {July},
abstract = {To rapidly learn a new task, it is often essential for agents to explore efficiently -- especially when performance matters from the first timestep. One way to learn such behaviour is via meta-learning. Many existing methods however rely on dense rewards for meta-training, and can fail catastrophically if the rewards are sparse. Without a suitable reward signal, the need for exploration during meta-training is exacerbated. To address this, we propose HyperX, which uses novel reward bonuses for meta-training to explore in approximate hyper-state space (where hyper-states represent the environment state and the agent's task belief). We show empirically that HyperX meta-learns better task-exploration and adapts more successfully to new tasks than existing methods.},
url = {http://approjects.co.za/?big=en-us/research/publication/exploration-in-approximate-hyper-state-space-for-meta-reinforcement-learning/},
}