xpag.agents.rljax_agents.util.optim.soft_update#
- soft_update(target_params, online_params, tau)#
Update target network using Polyak-Ruppert Averaging.
- Return type:
Mapping
[str
,Mapping
[str
,Array
]]
Update target network using Polyak-Ruppert Averaging.
Mapping
[str
, Mapping
[str
, Array
]]