Timezone: »

 
Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration
Oliver Groth · Markus Wulfmeier · Giulia Vezzani · Vibhavari Dasagi · Tim Hertweck · Roland Hafner · Nicolas Heess · Martin Riedmiller

@
in 4th Robot Learning Workshop: Self-Supervised and Lifelong Learning »

Curiosity-based reward schemes can present powerful exploration mechanisms which facilitate the discovery of solutions for complex, sparse or long-horizon tasks. However, as the agent learns to reach previously unexplored spaces and the objective adapts to reward new areas, many behaviours emerge only to disappear due to being overwritten by the constantly shifting objective. We argue that merely using curiosity for fast environment exploration or as a bonus reward for a specific task does not harness the full potential of this technique and misses useful skills. Instead, we propose to shift the focus towards retaining the behaviours which emerge during curiosity-based learning. We posit that these self-discovered behaviours serve as valuable skills in an agent's repertoire to solve related tasks. Our experiments demonstrate the continuous shift in behaviour throughout training and the benefits of a simple policy snapshot method to reuse discovered behaviour for transfer tasks.

Author Information

Oliver Groth (University of Oxford)
Markus Wulfmeier (DeepMind)
Giulia Vezzani (Google DeepMind)
Vibhavari Dasagi (Queensland University of Technology)
Tim Hertweck (DeepMind)
Roland Hafner (Google DeepMind)
Nicolas Heess (Google DeepMind)
Martin Riedmiller (DeepMind)

More from the Same Authors