Magnetic reconnection is a process that changes magnetic field topology in
highly conducting fluids. Within the standard Sweet-Parker model, this process
would be too slow to explain observations (e.g. solar flares). In reality, the
process must be ubiquitous as astrophysical fluids are magnetized and motions
of fluid elements necessarily entail crossing of magnetic frozen-in field lines
and magnetic reconnection. In the presence of turbulence, the reconnection is
independent of microscopic plasma properties, and may be much faster than
previously thought, as proposed in Lazarian & Vishniac (1999) and tested in
Kowal et al. (2009, 2012). However, the considered turbulence in the
Lazarian-Vishniac model was imposed externally. In this work we consider
reconnection-driven magnetized turbulence in realistic three-dimensional
geometry initiated by stochastic noise. We demonstrate through numerical
simulations that the stochastic reconnection is able to self-generate
turbulence through interactions between its outflows. We analyze the
statistical properties of velocity fluctuations using power spectra and
anisotropy scaling, which demonstrates that the reconnection produces
Kolmogorov-like turbulence, compatible with Goldreich-Sridhar (1995) model.
Anisotropy statistics are, however, strongly affected by the dynamics of
reconnection outflows. Once the broad turbulent region is formed, the typical
anisotropy scaling $l_\parallel \propto l_\perp^{2/3}$ is formed, especially
for high resolution models, were the broader range of scales is available. The
decay of reconnection outflows to turbulent-like fluctuations, characterized by
different anisotropy scalings, strongly depends on $\beta$ plasma. Moreover,
the estimated reconnection rates are weakly dependent on the resolution,
suggesting that no external processes are required to make reconnection fast.