PPO-CMA: Proximal Policy Optimization with Covariance Matrix Adaptation

October 05, 2018 ยท Declared Dead ยท ๐Ÿ› International Workshop on Machine Learning for Signal Processing

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Perttu Hรคmรคlรคinen, Amin Babadi, Xiaoxiao Ma, Jaakko Lehtinen arXiv ID 1810.02541 Category cs.LG: Machine Learning Cross-listed stat.ML Citations 70 Venue International Workshop on Machine Learning for Signal Processing Last Checked 3 months ago
Abstract
Proximal Policy Optimization (PPO) is a highly popular model-free reinforcement learning (RL) approach. However, we observe that in a continuous action space, PPO can prematurely shrink the exploration variance, which leads to slow progress and may make the algorithm prone to getting stuck in local optima. Drawing inspiration from CMA-ES, a black-box evolutionary optimization method designed for robustness in similar situations, we propose PPO-CMA, a proximal policy optimization approach that adaptively expands the exploration variance to speed up progress. With only minor changes to PPO, our algorithm considerably improves performance in Roboschool continuous control benchmarks. Our results also show that PPO-CMA, as opposed to PPO, is significantly less sensitive to the choice of hyperparameters, allowing one to use it in complex movement optimization tasks without requiring tedious tuning.
Community shame:
Not yet rated
Community Contributions

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

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted