Hierarchical Approaches for Reinforcement Learning in Parameterized Action Space
By Ermo Wei, Drew Wicke, Sean Luke. 2018
37 citations recorded by the source corpus.
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. We demonstrate that these methods outperform the state of the art method, Parameterized Action DDPG, on test domains.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Saurabh Gupta
- Abhinav Kumar Gupta
- Shubham Tulsiani
- Rohan Chitnis
- Yingfeng Chen
- Hongyao Tang
- Changjie Fan
- Jianye Hao
Citations in the corpus
- Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action Spaces (2019, methodology): “In this work, we consider a Cooperative Stochastic Game [Wei et al. , 2018a] in partially observable settings modeled as a tuple { S, U, r, P, γ, H, N } .”
- Efficient Bimanual Manipulation Using Learned Task Schemas (2019, background): “Recent work has addressed deep reinforcement learning for PAMDP s [11], [12], by learning policies that output both the discrete skill and continuous parameter selections at each timestep.”