Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning

May 24, 2022 Β· Declared Dead Β· πŸ› IEEE Robotics and Automation Letters

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Jinning Li, Chen Tang, Masayoshi Tomizuka, Wei Zhan arXiv ID 2205.11790 Category cs.RO: Robotics Cross-listed eess.SY Citations 71 Venue IEEE Robotics and Automation Letters Last Checked 5 months ago
Abstract
Offline Reinforcement learning (RL) has shown potent in many safe-critical tasks in robotics where exploration is risky and expensive. However, it still struggles to acquire skills in temporally extended tasks. In this paper, we study the problem of offline RL for temporally extended tasks. We propose a hierarchical planning framework, consisting of a low-level goal-conditioned RL policy and a high-level goal planner. The low-level policy is trained via offline RL. We improve the offline training to deal with out-of-distribution goals by a perturbed goal sampling process. The high-level planner selects intermediate sub-goals by taking advantages of model-based planning methods. It plans over future sub-goal sequences based on the learned value function of the low-level policy. We adopt a Conditional Variational Autoencoder to sample meaningful high-dimensional sub-goal candidates and to solve the high-level long-term strategy optimization problem. We evaluate our proposed method in long-horizon driving and robot navigation tasks. Experiments show that our method outperforms baselines with different hierarchical designs and other regular planners without hierarchy in these complex tasks.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Robotics

Died the same way β€” πŸ‘» Ghosted