Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic Locomotion

October 14, 2022 Β· Declared Dead Β· πŸ› IEEE International Conference on Robotics and Automation

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

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Lev Grossman, Brian Plancher arXiv ID 2210.08065 Category cs.RO: Robotics Cross-listed cs.LG Citations 7 Venue IEEE International Conference on Robotics and Automation Last Checked 4 months ago
Abstract
Deep reinforcement learning (DRL) is one of the most powerful tools for synthesizing complex robotic behaviors. But training DRL models is incredibly compute and memory intensive, requiring large training datasets and replay buffers to achieve performant results. This poses a challenge for the next generation of field robots that will need to learn on the edge to adapt to their environment. In this paper, we begin to address this issue through observation space quantization. We evaluate our approach using four simulated robot locomotion tasks and two state-of-the-art DRL algorithms, the on-policy Proximal Policy Optimization (PPO) and off-policy Soft Actor-Critic (SAC) and find that observation space quantization reduces overall memory costs by as much as 4.2x without impacting learning performance.
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