Hierarchical Approaches for Reinforcement Learning in Parameterized Action Space

Understand

We explore Deep Reinforcement Learning in a parameterized action space.

• Specifically, we investigate how to achieve sample-efficient end-to-end training in these tasks.
• We propose a new compact architecture for the tasks where the parameter policy is conditioned on the output of the discrete action policy.
• We also propose two new methods based on the state-of-the-art algorithms Trust Region Policy Optimization (TRPO) and Stochastic Value Gradient (SVG) to train such an architecture.