Timezone: »

What Can Learned Intrinsic Rewards Capture?
Zeyu Zheng · Junhyuk Oh · Matteo Hessel · Zhongwen Xu · Manuel Kroiss · Hado van Hasselt · David Silver · Satinder Singh

Tue Jul 14 07:00 AM -- 07:45 AM & Tue Jul 14 06:00 PM -- 06:45 PM (PDT) @ Virtual #None

The objective of a reinforcement learning agent is to behave so as to maximise the sum of a suitable scalar function of state: the reward. These rewards are typically given and immutable. In this paper, we instead consider the proposition that the reward function itself can be a good locus of learned knowledge. To investigate this, we propose a scalable meta-gradient framework for learning useful intrinsic reward functions across multiple lifetimes of experience. Through several proof-of-concept experiments, we show that it is feasible to learn and capture knowledge about long-term exploration and exploitation into a reward function. Furthermore, we show that unlike policy transfer methods that capture how'' the agent should behave, the learned reward functions can generalise to other kinds of agents and to changes in the dynamics of the environment by capturingwhat'' the agent should strive to do.

Author Information

Zeyu Zheng (University of Michigan)
Junhyuk Oh (DeepMind)
Matteo Hessel (Deep Mind)
Zhongwen Xu (DeepMind)
Manuel Kroiss (DeepMind)
Hado van Hasselt (DeepMind)
David Silver (Google DeepMind)
Satinder Singh (DeepMind)

More from the Same Authors