6c44fb28fecdb666182e2951b7b1cbe9cf198ff1,baselines/her/rollout.py,RolloutWorker,generate_rollouts,#RolloutWorker#,64

Before Change

            ag_new = np.empty((self.rollout_batch_size, self.dims["g"]))
            success = np.zeros(self.rollout_batch_size)
            // compute new states and observations
            for i in range(self.rollout_batch_size):
                try:
                    // We fully ignore the reward here because it will have to be re-computed
                    // for HER.
                    curr_o_new, _, _, info = self.envs[i].step(u[i])
                    if "is_success" in info:
                        success[i] = info["is_success"]
                    o_new[i] = curr_o_new["observation"]
                    ag_new[i] = curr_o_new["achieved_goal"]
                    for idx, key in enumerate(self.info_keys):
                        info_values[idx][t, i] = info[key]
                    if self.render:
                        self.envs[i].render()
                except MujocoException as e:
                    return self.generate_rollouts()

            if np.isnan(o_new).any():
                self.logger.warn("NaN caught during rollout generation. Trying again...")
                self.reset_all_rollouts()
                return self.generate_rollouts()

After Change

                // after a reset
                break

            for i, info_dict in enumerate(info):
                for idx, key in enumerate(self.info_keys):
                    info_values[idx][t, i] = info[i][key]

            if np.isnan(o_new).any():
                self.logger.warn("NaN caught during rollout generation. Trying again...")
                self.reset_all_rollouts()
                return self.generate_rollouts()

Instances