A unified strategy for implementing curiosity and empowerment driven reinforcement learning

no code implementations • 18 Jun 2018 • Ildefons Magrans de Abril, Ryota Kanai

Curiosity reward informs the agent about the relevance of a recent agent action, whereas empowerment is implemented as the opposite information flow from the agent to the environment that quantifies the agent's potential of controlling its own future.

reinforcement-learning Reinforcement Learning (RL)

Curiosity-driven reinforcement learning with homeostatic regulation

no code implementations • 23 Jan 2018 • Ildefons Magrans de Abril, Ryota Kanai

We propose a curiosity reward based on information theory principles and consistent with the animal instinct to maintain certain critical parameters within a bounded range.

reinforcement-learning Reinforcement Learning (RL)