Core Concepts
Reinforcement learning on high-dimensional and complex problems relies on abstraction for improved efficiency and generalization.
Stats
Reinforcement learning on high-dimensional and complex problems relies on abstraction for improved efficiency and generalization.
Our policy gradient results allow for leveraging approximate symmetries of the environment for policy optimization.
Our method’s ability to utilize MDP homomorphisms for representation learning leads to improved performance.
Quotes
"Our method’s ability to utilize MDP homomorphisms for representation learning leads to improved performance."
"Our policy gradient results allow for leveraging approximate symmetries of the environment for policy optimization."