Timeline for Deep Q-learning is not performing well when there are several enemies
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| S Feb 10, 2019 at 21:18 | history | suggested | nbro | CC BY-SA 4.0 |
A few improvements
|
| Feb 10, 2019 at 11:53 | review | Suggested edits | |||
| S Feb 10, 2019 at 21:18 | |||||
| Feb 10, 2019 at 10:59 | comment | added | Brale | You have to provide a bit more details. What is the shape of your neural network? What are you using as input, state features or images? Are you providing state observation + action as the input or only state observation? How does the output look like, are there 5 nodes each for specific action or is it only a single output node for the specific action you provided as a part of the input. What are the rewards for your environment? Are you using exploratory policy? Are you using experience replay? Are you using separate networks? Are you providing enough training time? | |
| Feb 10, 2019 at 10:30 | answer | added | DrMcCleod | timeline score: 1 | |
| Feb 10, 2019 at 10:25 | review | First posts | |||
| Feb 10, 2019 at 20:32 | |||||
| Feb 10, 2019 at 10:22 | history | asked | Savco | CC BY-SA 4.0 |