Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers

Gautham Vasan, Mohamed Elsayed, Seyed Alireza Azimi, Jiamin He, Fahim Shahriar, Colin Bellinger, Martha White, A. Rupam Mahmood

Keywords: Reinforcement Learning, Robotics, Deep Learning, Incremental Learning, Real-time Learning

TL;DR: We introduce Action Value Gradient (AVG), a novel incremental policy gradient method for real-time learning on robots with limited onboard computation, eliminating the need for large replay buffers, target networks or batch updates.

Abstract: Modern deep policy gradient methods achieve effective performance on simulated robotic tasks, but they all require large replay buffers or expensive batch updates, or both, making them incompatible for real systems with resource-limited computers. We show that these methods fail catastrophically when limited to small replay buffers or during *incremental learning*, where updates only use the most recent sample without batch updates or a replay buffer. We propose a novel incremental deep policy gradient method --- *Action Value Gradient (AVG)* and a set of normalization and scaling techniques to address the challenges of instability in incremental learning. On robotic simulation benchmarks, we show that AVG is the only incremental method that learns effectively, often achieving final performance comparable to batch policy gradient methods. This advancement enabled us to show for the first time effective deep reinforcement learning with real robots using only incremental updates, employing a robotic manipulator and a mobile robot.

Primary Area: Reinforcement learning

Submission Number: 18724