update todo
This commit is contained in:
parent
57cead431d
commit
4765104c7a
1 changed files with 3 additions and 1 deletions
4
_NOTICE
4
_NOTICE
|
@ -5,12 +5,14 @@ however, feel free to copy any snippets of code you find useful.
|
||||||
TODOs: (that i can remember right now)
|
TODOs: (that i can remember right now)
|
||||||
- finish implementing backprop
|
- finish implementing backprop
|
||||||
- replace evolution strategy algorithm with
|
- replace evolution strategy algorithm with
|
||||||
something that utilizes gradients like PPO
|
something that utilizes backprop like PPO
|
||||||
- settle on a network architecture
|
- settle on a network architecture
|
||||||
- normalize and/or embed sprite inputs
|
- normalize and/or embed sprite inputs
|
||||||
- fix lag-frames skipped-inputs bug
|
- fix lag-frames skipped-inputs bug
|
||||||
|
- detect frames when Mario is in a controllable state
|
||||||
- fix offscreen sprites sometimes being visible to network
|
- fix offscreen sprites sometimes being visible to network
|
||||||
- add some detection for enemies later in the game
|
- add some detection for enemies later in the game
|
||||||
|
- compute how many input neurons the network needs instead of hardcoding
|
||||||
|
|
||||||
naive:
|
naive:
|
||||||
- learn any combination of buttons, starting from title screen
|
- learn any combination of buttons, starting from title screen
|
||||||
|
|
Loading…
Add table
Reference in a new issue