From 4765104c7ab974895cc1f81eb2c1d4ad431f9c36 Mon Sep 17 00:00:00 2001 From: Connor Olding Date: Fri, 23 Mar 2018 09:33:02 +0100 Subject: [PATCH] update todo --- _NOTICE | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/_NOTICE b/_NOTICE index a6f0389..33299d2 100644 --- a/_NOTICE +++ b/_NOTICE @@ -5,12 +5,14 @@ however, feel free to copy any snippets of code you find useful. TODOs: (that i can remember right now) - finish implementing backprop - replace evolution strategy algorithm with - something that utilizes gradients like PPO + something that utilizes backprop like PPO - settle on a network architecture - normalize and/or embed sprite inputs - fix lag-frames skipped-inputs bug +- detect frames when Mario is in a controllable state - fix offscreen sprites sometimes being visible to network - add some detection for enemies later in the game +- compute how many input neurons the network needs instead of hardcoding naive: - learn any combination of buttons, starting from title screen