lambda_return#
- hybrid_aif.train.lambda_return(value, reward, disc, return_lambda)[source]#
DreamerV3’s λ-return over an imagined trajectory.
valueis(H+1,), the critic ats_0 … s_H;rewardanddiscare(H,)indexed by the step taken (reward[k]is collected moving intos_{k+1},disc[k] = discount · cont(s_{k+1})). Returns(H,), entrykthe return estimate ats_k, bootstrapped byvalue[H].