ROTONDWA MAVHENGANI

Dynamic Software Developer with over 2.5 years at FNB Forex, excelling in Java SQL and machine learning etc. Renowned for innovative problem-solving and delivering robust software solutions, I foster collaboration and mentor peers, enhancing team performance. My expertise in payment processing and API development drives secure, efficient transactions.

Super Mario Bros Procedural Content Generation via Reinforcement, Investigated how reinforcement learning can be used to train level-designing agents., Framed level design as a game, where the content generator itself is learned., Used reinforcement learning to learn how to take the next action so that the expected final level quality is maximized., Transformed two-dimensional level design problems into Markov decision processes., Demonstrated that reinforcement learning can be effectively used when few or no examples exist to train from., Showed that the trained generator is very fast and efficient., Applied these methods to three different game environments, showcasing the versatility and effectiveness of the approach., This research represents a new approach to procedural content generation in games, highlighting the potential of reinforcement learning in creative and technical problem-solving.