Hi Marcus, I've found at least one error in the CMA ES implementation in ensmallen:
in line *209* and *214* where *p_sigma* is computed, the choleski factor of the covariance matrix is used, while the original algorithm takes the inverse root of the covariance matrix. (eq *44*, page *29* in the tutorial https://arxiv.org/pdf/1604.00772.pdf ). What is the best way to compute A^(-1/2) = BD^(-1)B^T in armadillo? I've stumbled upon the problem while trying to let cma es from ensmallen learn CartPole. Also, I have implemented the LM CMA (https://arxiv.org/abs/1511.00221), I've tested it on learning cartpole and rosenbrock. It outperforms CMA ES on rosenbrock in terms of computation time with 1000 params. I'd love to contribute it to ensmallen. I've tried to train it on the Breakout env, but somehow my computer seems to have problems, running both the learner and the gym api -- that is also one thing I need to solve. Btw I am really sorry to be so late with my proposal. I hope to upload it tonight, hope it is still OKay. Best Oleksandr
_______________________________________________ mlpack mailing list mlpack@lists.mlpack.org http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack