Did I find the right examples for you? yes no      Crawl my project      Python Jobs

All Samples(7)  |  Call(7)  |  Derive(0)  |  Import(0)

src/r/l/rlpy-HEAD/rlpy/MDPSolvers/ValueIteration.py   rlpy(Download)
 
                    if bellmanUpdates % self.log_interval == 0:
                        performance_return, _, _, _ = self.performanceRun()
                        self.logger.info(
                            '[%s]: BellmanUpdates=%d, Return=%0.4f' %
                np.inf)
            performance_return, performance_steps, performance_term, performance_discounted_return = self.performanceRun(
            )
            converged = weight_vec_change < self.convergence_threshold
            self.logger.info(

src/r/l/rlpy-HEAD/rlpy/MDPSolvers/PolicyIteration.py   rlpy(Download)
                        if bellmanUpdates % self.log_interval == 0:
                            performance_return, _, _, _ = self.performanceRun(
                            )
                            self.logger.info(
                                '[%s]: BellmanUpdates=%d, Return=%0.4f' %
            policy.representation.weight_vec = self.representation.weight_vec.copy()
            performance_return, performance_steps, performance_term, performance_discounted_return = self.performanceRun(
            )
            self.logger.info(
                'PI #%d [%s]: BellmanUpdates=%d, Policy Change=%d, Return=%0.4f, Steps=%d' % (

src/r/l/rlpy-HEAD/rlpy/MDPSolvers/TrajectoryBasedPolicyIteration.py   rlpy(Download)
 
            performance_return, performance_steps, performance_term, performance_discounted_return = self.performanceRun(
            )
            self.logger.info(
                'PI #%d [%s]: BellmanUpdates=%d, ||delta-weight_vec||=%0.4f, Return=%0.3f, steps=%d, features=%d' % (PI_iteration,
            self.representation.weight_vec = new_weight_vec
            performance_return, performance_steps, performance_term, performance_discounted_return = self.performanceRun(
            )
            self.logger.info(
                '#%d [%s]: Samples=%d, ||weight-Change||=%0.4f, Return = %0.4f' %

src/r/l/rlpy-HEAD/rlpy/MDPSolvers/TrajectoryBasedValueIteration.py   rlpy(Download)
                converged_trajectories = 0
            performance_return, performance_steps, performance_term, performance_discounted_return = self.performanceRun(
            )
            converged = converged_trajectories >= self.MIN_CONVERGED_TRAJECTORIES
            self.logger.info(