baselines/gail/trpo_mpi.py [269:282]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                assert np.isfinite(stepdir).all()
                shs = .5*stepdir.dot(fisher_vector_product(stepdir))
                lm = np.sqrt(shs / max_kl)
                # logger.log("lagrange multiplier:", lm, "gnorm:", np.linalg.norm(g))
                fullstep = stepdir / lm
                expectedimprove = g.dot(fullstep)
                surrbefore = lossbefore[0]
                stepsize = 1.0
                thbefore = get_flat()
                for _ in range(10):
                    thnew = thbefore + fullstep * stepsize
                    set_from_flat(thnew)
                    meanlosses = surr, kl, *_ = allmean(np.array(compute_losses(*args)))
                    improve = surr - surrbefore
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



baselines/trpo_mpi/trpo_mpi.py [323:336]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            assert np.isfinite(stepdir).all()
            shs = .5*stepdir.dot(fisher_vector_product(stepdir))
            lm = np.sqrt(shs / max_kl)
            # logger.log("lagrange multiplier:", lm, "gnorm:", np.linalg.norm(g))
            fullstep = stepdir / lm
            expectedimprove = g.dot(fullstep)
            surrbefore = lossbefore[0]
            stepsize = 1.0
            thbefore = get_flat()
            for _ in range(10):
                thnew = thbefore + fullstep * stepsize
                set_from_flat(thnew)
                meanlosses = surr, kl, *_ = allmean(np.array(compute_losses(*args)))
                improve = surr - surrbefore
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -