Reinforcement Learning
Author : Shubha Manikarnike Submitted on : 5 Dec 2020 Abstract – This paper is a review of the paper “Reinforcement Learning for Supply Chain Optimization” (https://www.researchgate.net/publication/328676423_Reinforcement_learning_for_supply_chain_optimization) and helps us understand how to model the supply chain environment as a Reinforcement Learning problem and how to model the DDPG algorithm can be used to successfully […]
Author : Shubha Manikarnike Submitted on : 5 Sep 2020 Abstract – This paper explains the AlphaGoZero algorithm which was developed by Google Deepmind. It achieved super human performance in the Game of GO. It discusses Monte Carlo Tree Search (MCTS) algorithm which is integrated with an Actor Critic approach. The agent learns how to […]
#CellStratAILab #disrupt4.0 #WeCreateAISuperstars #WhereLearningNeverStops In recent weeks, I had presented a session on “AlphaZero with Monte Carlo Tree Search” algorithm at the CellStrat AI Lab. This is an algorithm developed by Google Deepmind in 2016. It mastered the game of GO and beat the 18-time world champion at the time Lee Sedol. Go is an ancient Chinese abstract strategy […]
Introduction Moving up the value chain CellStrat would like to encourage discussions and webinars focusing on the application of AI in Real Life problem-solving. A beginning has already been made and this is another step in that direction. The use of Deep Learning and Reinforcement Learning to solve a complex Strategic Negotiation is a very […]
#CellStratAILab #disrupt4.0 #WeCreateAISuperstars #WhereLearningNeverStops Recently, I presented a session on Metric-based Meta Learning at the CellStrat AI Lab (where I am an AI Researcher). Metric-based Meta Learning might be considered a domain of Artificial General Intelligence (AGI). This is due to the fact that Meta Learning helps us create generalized systems with relatively less data. […]
#CellStratAILab #disrupt4.0 #WeCreateAISuperstars I presented a session on Multi-Agent RL recently at the CellStrat AI Lab. Introduction :- In the normal Reinforcement Learning setup, you have one agent which interacts with the environment. It uses the Observation from the environment, performs actions and observes the rewards. In real life, many applications will involve several agents […]
This post discusses temporal difference (TD) methods, used in Reinforcement Learning. It contrasts TD methods with Monte Carlo (MC) methods and dynamic programming. You need to have a thorough understanding of Markov Decision Process (MDP) to understand this post. Prediction and Control : In general, RL methods have two components 1) Prediction / Evaluation : where […]
This post assumes that you have a strong understanding of the basics of Reinforcement Learning, MDP, DQN and Policy Gradient Algorithms. You can go through Policy Gradients to understand the derivation for Stochastic Policies In the previous post on Actor Critic, we saw the advantage of merging Value based and Policy based methods together. The […]
#CellStratAILab #disrupt4.0 #WeCreateAISuperstars #AlwaysUpskilling Reinforcement Learning (RL) refers to training agents with help of incentive-driven environments. RL typically involves a tuple of <state, action, reward> paradigm, which means that the agent has action choices to make in various states, and each action entails a potential reward. This also means that each state has a “value” […]
#CellStratAILab #disrupt4.0 #WeCreateAISuperstars #AlwaysUpskilling Minutes from Saturday 14th March 2020 AI Lab Workshop at BLR :- Session Presenter : SHUBHA M., Deep Reinforcement Learning Researcher, CellStrat AI Lab Last Saturday, our Reinforcement Learning Team Lead Shubha M. presented a fantastic presentation and workshop on Actor-Critic method used in RL. She also demonstrated a demo of this technique for Stock Market predictions. […]