spinup/algos/tf1/ppo/ppo.py [252:297]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    for epoch in range(epochs):
        for t in range(local_steps_per_epoch):
            a, v_t, logp_t = sess.run(get_action_ops, feed_dict={x_ph: o.reshape(1,-1)})

            o2, r, d, _ = env.step(a[0])
            ep_ret += r
            ep_len += 1

            # save and log
            buf.store(o, a, r, v_t, logp_t)
            logger.store(VVals=v_t)

            # Update obs (critical!)
            o = o2

            terminal = d or (ep_len == max_ep_len)
            if terminal or (t==local_steps_per_epoch-1):
                if not(terminal):
                    print('Warning: trajectory cut off by epoch at %d steps.'%ep_len)
                # if trajectory didn't reach terminal state, bootstrap value target
                last_val = 0 if d else sess.run(v, feed_dict={x_ph: o.reshape(1,-1)})
                buf.finish_path(last_val)
                if terminal:
                    # only save EpRet / EpLen if trajectory finished
                    logger.store(EpRet=ep_ret, EpLen=ep_len)
                o, ep_ret, ep_len = env.reset(), 0, 0

        # Save model
        if (epoch % save_freq == 0) or (epoch == epochs-1):
            logger.save_state({'env': env}, None)

        # Perform PPO update!
        update()

        # Log info about epoch
        logger.log_tabular('Epoch', epoch)
        logger.log_tabular('EpRet', with_min_and_max=True)
        logger.log_tabular('EpLen', average_only=True)
        logger.log_tabular('VVals', with_min_and_max=True)
        logger.log_tabular('TotalEnvInteracts', (epoch+1)*steps_per_epoch)
        logger.log_tabular('LossPi', average_only=True)
        logger.log_tabular('LossV', average_only=True)
        logger.log_tabular('DeltaLossPi', average_only=True)
        logger.log_tabular('DeltaLossV', average_only=True)
        logger.log_tabular('Entropy', average_only=True)
        logger.log_tabular('KL', average_only=True)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



spinup/algos/tf1/vpg/vpg.py [229:274]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    for epoch in range(epochs):
        for t in range(local_steps_per_epoch):
            a, v_t, logp_t = sess.run(get_action_ops, feed_dict={x_ph: o.reshape(1,-1)})

            o2, r, d, _ = env.step(a[0])
            ep_ret += r
            ep_len += 1

            # save and log
            buf.store(o, a, r, v_t, logp_t)
            logger.store(VVals=v_t)

            # Update obs (critical!)
            o = o2

            terminal = d or (ep_len == max_ep_len)
            if terminal or (t==local_steps_per_epoch-1):
                if not(terminal):
                    print('Warning: trajectory cut off by epoch at %d steps.'%ep_len)
                # if trajectory didn't reach terminal state, bootstrap value target
                last_val = 0 if d else sess.run(v, feed_dict={x_ph: o.reshape(1,-1)})
                buf.finish_path(last_val)
                if terminal:
                    # only save EpRet / EpLen if trajectory finished
                    logger.store(EpRet=ep_ret, EpLen=ep_len)
                o, ep_ret, ep_len = env.reset(), 0, 0

        # Save model
        if (epoch % save_freq == 0) or (epoch == epochs-1):
            logger.save_state({'env': env}, None)

        # Perform VPG update!
        update()

        # Log info about epoch
        logger.log_tabular('Epoch', epoch)
        logger.log_tabular('EpRet', with_min_and_max=True)
        logger.log_tabular('EpLen', average_only=True)
        logger.log_tabular('VVals', with_min_and_max=True)
        logger.log_tabular('TotalEnvInteracts', (epoch+1)*steps_per_epoch)
        logger.log_tabular('LossPi', average_only=True)
        logger.log_tabular('LossV', average_only=True)
        logger.log_tabular('DeltaLossPi', average_only=True)
        logger.log_tabular('DeltaLossV', average_only=True)
        logger.log_tabular('Entropy', average_only=True)
        logger.log_tabular('KL', average_only=True)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -