Expected policy gradients
We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected sarsa, EPG integrates across the action when estimating the gradient, instead of relying only on the action in the sampl...
| Prif Awduron: | , |
|---|---|
| Fformat: | Conference item |
| Cyhoeddwyd: |
Association for the Advancement of Artificial Intelligence
2018
|