lucidrains 2a902eaaf7 allow reward tokens to be attended to as state optionally, DT-esque. figure out multi-agent scenario once i get around to it

2025-10-16 06:41:02 -07:00

..

__init__.py

for the value head, we will go for symexp encoding as well (following the "stop regressing" paper from Farebrother et al), also use layernormed mlp given recent papers

2025-10-08 07:37:34 -07:00

dreamer4.py

allow reward tokens to be attended to as state optionally, DT-esque. figure out multi-agent scenario once i get around to it

2025-10-16 06:41:02 -07:00

trainers.py

add the noising of the latent context during generation, technique i think was from EPFL, or perhaps some google group that built on top of EPFL work

2025-10-07 09:37:37 -07:00