lucidrains 2fc3b17149 take a gradient step with behavioral clone trainer, make sure it works with and without actions and rewards

2025-10-21 10:20:08 -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

oops

2025-10-21 09:50:07 -07:00

mocks.py

prepare a mock for interacting with online env

2025-10-21 09:03:20 -07:00

trainers.py

take a gradient step with behavioral clone trainer, make sure it works with and without actions and rewards

2025-10-21 10:20:08 -07:00