Jekyll2023-03-10T00:11:21-08:00https://han8931.github.io/feed.xmlHan Cheol Moonpersonal descriptionHan Cheol Moonhancheol001@e.ntu.edu.sgReinforcement Learning Study Note2023-03-10T00:00:00-08:002023-03-10T00:00:00-08:00https://han8931.github.io/posts/2023/03/lecture-post-1<p>There are already a number of excellent tutorials and lectures on Reinforcement Learning (RL) available, but I often find that these do not provide enough detail or explanation of the formulas behind them. This may be because a lot of the concepts are assumed to be obvious or straightforward.</p>
<p>This can be a problem for someone like me who has a weak background in mathematics, but wants to gain a comprehensive understanding of RL. To address this, I am attempting to explain the theory as clearly as possible, using plenty of examples and details. Moreover, many Python RL implementations rely heavily on external libraries or are overly simplistic. Thus, I am endeavoring to bridge the gap between theory and implementation. Finally, I want to acknowledge that this work is based on numerous sources, and I am forever indebted to them.</p>
<p><a href="https://github.com/Han8931/reinforcement_learning_note">Link</a></p>Han Cheol Moonhancheol001@e.ntu.edu.sgThere are already a number of excellent tutorials and lectures on Reinforcement Learning (RL) available, but I often find that these do not provide enough detail or explanation of the formulas behind them. This may be because a lot of the concepts are assumed to be obvious or straightforward.Multi-Layer Perceptron from Scratch2023-03-10T00:00:00-08:002023-03-10T00:00:00-08:00https://han8931.github.io/posts/2023/03/lecture-post-2<p>This is an implementation of multi-layer perceptron and its training with backpropagation from scratch using Numpy.</p>
<p><a href="https://colab.research.google.com/drive/1IAonxZnZjJb0_xUVWHt5atIxaI5GTJQ2?usp=sharing">ColabLink</a></p>Han Cheol Moonhancheol001@e.ntu.edu.sgThis is an implementation of multi-layer perceptron and its training with backpropagation from scratch using Numpy.