Fix metadata

This PR fixes the metadata tags, so that it properly gets found at https://huggingface.co/models?pipeline_tag=reinforcement-learning&sort=trending

README.md

@@ -1,9 +1,12 @@
 ---
-pipeline_tag: reinforcement-learning, diffusion, world-models
+tags:
+- diffusion
+- world-models
+pipeline_tag: reinforcement-learning
 ---
 
 Pretrained models for the paper "Diffusion for World Modeling: Visual Details Matter in Atari".
 
 - Paper: [https://arxiv.org/abs/2405.12399](https://arxiv.org/abs/2405.12399)
 - Code: [https://github.com/eloialonso/diamond](https://github.com/eloialonso/diamond)
-- Webpage: [https://diamond-wm.github.io](https://diamond-wm.github.io)
+- Webpage: [https://diamond-wm.github.io](https://diamond-wm.github.io)