Teaching a computer to play video games has generally been seen as a reasonable benchmark for developing new AI techniques. In recent years, extensive research has been completed to develop reinforcement learning (RL) algorithms to play various Atari 2600 games, resulting in new applications of algorithms such as Deep Q-Learning or Policy Gradient that outperform humans. However, games from Super Nintendo Entertainment System (SNES) are far more complicated than Atari 2600 games as many of these state-of-the-art algorithms still struggle to perform on this platform. In this paper, we present a new platform to research algorithms on SNES games and investigate NeuroEvolution of Augmenting Topologies (NEAT) as a possible approach to develop algorithms that outperform humans in SNES games.

It has been proved that when the production probabilities of an unambiguous context-free grammar G are estimated by the relative frequencies of the corresponding productions in a sample S from the language L(G) generated by G, the expected derivation length and the expected word length of the words in L(G) are precisely equal to the mean derivation length and the mean world length of the words in the same S, respectively.

Single error correcting-double error detecting (SEC-DED) codes have been successfully used in computer memories for reliability. In the present-day technology of very large scale integration storage arrays bit error correction as well as byte error detection/byte error correction become extremely important. We devise here classes of cyclic codes with generator of the form (xb -1) p(x) for some suitable irreducible polynomial p(x) which provide 1) single byte error correction (SBEC), and 2) single error correction, double error detection, and byte error detection (SEC-DED-BED) codes. The codes have high information rate and are easy to implement. This general class of codes combines elegantly the results of several researchers and in some cases extends their results.