| Download | - View final version: Deep policy gradient methods without batch updates, target networks, or replay buffers (PDF, 591.4 MiB)
|
|---|
| Link | https://proceedings.neurips.cc/paper_files/paper/2024/file/019ef89617d539b15ed610ce8d1b76e1-Paper-Conference.pdf |
|---|
| Author | Search for: Vasan, Gautham; Search for: Elsayed, Mohamed; Search for: Azimi, Alireza; Search for: He, Jiamin; Search for: Shariar, Fahim; Search for: Bellinger, Colin1ORCID identifier: https://orcid.org/0000-0002-3567-7834; Search for: White, Martha; Search for: Rupam Mahmood A. |
|---|
| Affiliation | - National Research Council Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | 38th Conference on Neural Information Processing Systems, NeurIPS 2024, December 10-15, 2024, Vancouver, BC, Canada |
|---|
| 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. |
|---|
| Publication date | 2024-12-10 |
|---|
| Publisher | Neural Information Processing Systems Foundation |
|---|
| Licence | |
|---|
| In | |
|---|
| Series | |
|---|
| Related data | |
|---|
| Other format | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 14988d94-5936-492f-bcd1-18cdd3161579 |
|---|
| Record created | 2025-04-10 |
|---|
| Record modified | 2025-04-14 |
|---|
