Thompson Sampling based Monte Carlo Tree Search for MDPs and POMDPs
-
Updated
Jun 20, 2016 - C++
Thompson Sampling based Monte Carlo Tree Search for MDPs and POMDPs
Hierarchical Online Planning and Reinforcement Learning on Taxi
ELEPHANT environment is for training Markov Decision Process agents provides macros definitions that make the training programs easy to read. It implements the concepts of training stages, training bots that communicate with the agents, and atomic keys used to build the communication messages. The keys can be shared among the bots on different s…
Benchmarking Distributed Inexact Policy Iteration for Large-Scale Markov Decision Processes
Knowledge Representation Using Markov Decision Process (MDP) for Intelligent Decision-Making in Student Advising Systems.
A minimalist, low-latency, HFT CME MDP 3.0 C++ market data feed handler implementing all required features
A Modern Probabilistic Model Checker
Add a description, image, and links to the mdp topic page so that developers can more easily learn about it.
To associate your repository with the mdp topic, visit your repo's landing page and select "manage topics."