Add a link to the brax visualization notebook in the notebooks README

examples/notebooks/README.md

@@ -17,7 +17,7 @@ pip install 'gym[box2d]'
 The notebook examples are listed below:
 
 - **[Gym Experiments with PGPE and CoSyNE](Gym_Experiments_with_PGPE_and_CoSyNE.ipynb):** demonstrates how you can solve "LunarLanderContinuous-v2" using both `PGPE` and `CoSyNE` following the configurations described in [the paper proposing ClipUp](https://dl.acm.org/doi/abs/10.1007/978-3-030-58115-2_36) and [the JMLR paper on the CoSyNE algorithm](https://www.jmlr.org/papers/volume9/gomez08a/gomez08a.pdf).
-- **[Brax Experiments with PGPE](Brax_Experiments_with_PGPE.ipynb):** demonstrates how you can solve the brax task "humanoid" using PGPE, with GPU support, if available.
+- **[Brax Experiments with PGPE](Brax_Experiments_with_PGPE.ipynb):** demonstrates how you can solve the brax task "humanoid" using PGPE, with GPU support, if available. See also [Brax_Experiments_Visualization.ipynb](Brax_Experiments_Visualization.ipynb) for visualizing evolved brax policies.
 - **[Minimizing Lennard-Jones Atom Cluster Potentials](Minimizing_Lennard-Jones_Atom_Cluster_Potentials.ipynb):** recreates experiments from [the paper introducing `SNES`](https://dl.acm.org/doi/abs/10.1145/2001576.2001692), showing that the algorithm can effectively solve the challenging task of [minimising Lennard-Jones atom cluster potentials](https://pubs.acs.org/doi/abs/10.1021/jp970984n).
 - **[Model Predictive Control with CEM](Model_Predictive_Control_with_CEM/):** demonstrates the application of [the Cross-Entropy Method `CEM`](https://link.springer.com/article/10.1023/A:1010091220143) to Model Predictive Control (MPC) of the MuJoCo task named "Reacher-v4".
 - **[Training MNIST30K](Training_MNIST30K.ipynb):** recreates experiments [from a recent paper](https://www.deepmind.com/publications/non-differentiable-supervised-learning-with-evolution-strategies-and-hybrid-methods) which demonstrates that `SNES` can be used to solve supervised learning problems. The script in particular recreates the training of the 30K-parameter 'MNIST30K' model on the MNIST dataset, but can easily be reconfigured to recreate other experiments from that paper.