Evolved Policy Gradients

Understand

We propose a metalearning approach for learning gradient-based reinforcement learning (RL) algorithms.

• The idea is to evolve a differentiable loss function, such that an agent, which optimizes its policy to minimize this loss, will achieve high rewards.
• The loss is parametrized via temporal convolutions over the agent's experience.
• Because this loss is highly flexible in its ability to take into account the agent's history, it enables fast task learning.