Contemporary Reinforcement Learning (RL) use cases include various automated operational decisions, like those of automated warehouse operations, vehicle routing, manufacturing systems, supply and value chains, recommender systems of online marketplaces, traffic signal control, drones and other autonomous vehicle driving, etc. Including ChatGPT! In short, RL models have a significant role in any inter-active decision making context.
The major objective of this workshop was to familarize the participants with various basic and fundamental building blocks in sequential decision making techniques. Emphasis during this 2 days Workshop was to provide an intuitive understanding of basic concepts related to MDP and RL.
We thank IIM Banglaore for providing us this opporunity. Prof. N. Hemachandra is spending his sabbatical at IIM Banglaore, and Prashant Trivedi is partially supported by IIM Bangalore, inlcuding stay, food and travel.