Scalable MCTS for team scenarios

Value iteration solver for MDPs

Concise and friendly interfaces for defining MDP and POMDP models for use with POMDPs.jl solvers

Problem models for testing POMDPs.jl

The PO-UCT algorithm (aka POMCP) implemented in Julia

Julia library for deep reinforcement learning

Simple particle filter implementation in Julia - works with POMDPs.jl models or others.

Online solver based on Monte Carlo tree search for POMDPs with continuous state, action, and observation spaces.

Implementation of the Deep Q-learning algorithm to solve MDPs

Monte Carlo Tree Search for Markov decision processes using the POMDPs.jl framework