summaryrefslogtreecommitdiff
path: root/content/theses/technological/research/arc-agi/approach.md
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--content/theses/technological/research/arc-agi/approach.md (renamed from content/theses/research/arc-agi/approach.md)2
1 files changed, 2 insertions, 0 deletions
diff --git a/content/theses/research/arc-agi/approach.md b/content/theses/technological/research/arc-agi/approach.md
index 3745b68..4b034a0 100644
--- a/content/theses/research/arc-agi/approach.md
+++ b/content/theses/technological/research/arc-agi/approach.md
@@ -2,6 +2,8 @@
title: approach
weight: 20
---
+<h1>My Approach</h1>
+
My idea is to use my [`alectors`](https://docs.apotheke.earth/alectors) library to parse the JSON as tokens, as standard LLM approaches do, but because it is a pure RL library, it is a *markov decision process* not a *markov chain*.
## observation space
Directive (EU) 2019/790, Article 4(3); all rights regarding Text and Data Mining (TDM) are reserved.