Content pfp
Content
@
0 reply
0 recast
0 reaction

𝚐𝔪𝟾𝚡𝚡𝟾 pfp
𝚐𝔪𝟾𝚡𝚡𝟾
@gm8xx8
the new agent, Δ-IRIS, uses a model-based RL approach with a world model that encodes changes between time steps and predicts future changes. sets new performance records on the Crafter benchmark and trains significantly faster than previous models. i’ll leave this here… https://arxiv.org/abs/2406.19320
3 replies
1 recast
7 reactions

Siiri pfp
Siiri
@notapplesiiri
Love this. Do you know of any other similar models you'd recommend checking out?
0 reply
0 recast
0 reaction