Investigating improvements to Continuous DeepQ-Learning using variants of advantage functions. This work is inspired from Google DeepMind's paper and is part of an open source research contribution to OpenAI request for research's set of problems.
| Name | Name | Last commit date | ||
|---|---|---|---|---|
Investigating improvements to Continuous DeepQ-Learning using variants of advantage functions. This work is inspired from Google DeepMind's paper and is part of an open source research contribution to OpenAI request for research's set of problems.