Can I read Supervised Learning in Upside Down RL on EtoBox?
Supervised Learning in Upside Down RL by Azzeddine CHENINE is a document available to read on EtoBox.
What is Supervised Learning in Upside Down RL about?
The document discusses Upside Down Reinforcement Learning (UDRL), which redefines reinforcement learning by using supervised learning to predict actions based on returns. UDRL can be applied across various learning paradigms, including imitation learning, offline RL, goal-conditioned RL, and meta-RL, allowing a single agent architecture to learn in diverse settings. The authors present experimental results demonstrating the effectiveness of UDRL in a classic control problem, highlighting its potential as a
- Author
- Azzeddine CHENINE
- Language
- EN