lucidrains b02abc7a8a able to store the agent embeddings during rollouts with imagination or environment, for efficient policy optimization (but will also allow for finetuning world model for the heads)

2025-10-28 09:01:29 -07:00

..

__init__.py

first pass through gathering experience with a mock env for online rl

2025-10-22 08:32:46 -07:00

dreamer4.py

able to store the agent embeddings during rollouts with imagination or environment, for efficient policy optimization (but will also allow for finetuning world model for the heads)

2025-10-28 09:01:29 -07:00

mocks.py

redo so that max timesteps is treated as truncation at the last timestep, then allow for accepting the truncation signal from the environment and reuse same logic

2025-10-28 08:04:48 -07:00

trainers.py

redo so lens is always the episode length, including the bootstrap value timestep, and use is_truncated to mask out the bootstrap node from being learned on

2025-10-27 08:06:21 -07:00