Pinned Repositories
RaceGame
A modified verions of the Baum-Welch algorithm to learn Hidden Options from imitation. A simplified driving simulation is included.
HSRRL
A reinforcement learning reactive framework for c++. It should make easier to use and test RL algorithms, including hierarchical reinforcement learning ones, such as Option Learning, and reward abstraction via Expectation Gradient
NHRL
An adaptive algorithm, which should abstract temporally extended actions online, without the need for additional background information (besides a Markovian description of the environment). Several Reinforcement Learning algorithms where embedded in a Hierarchy of policies, among which n-step QL, Expected Sarsa, LSTM neural networks (for Q value learning), Deep Mind's Deep Q-learning architecture, and simultaneous off-policy training (of all abstract actions).
ToMCT
Theory of Mind agents (generic level) playing in a Colored Trails task
grasp
Controller for robotic manipulator (6 DOF). The systems uses HOG and Support Vector Machines to classify an object's position and determine how to grasp it.
CPP_SocketWrapper
C++ wrapper for Server/Client TCP Sockets
shell
A c shell with piping, background processes, and string parsing
AP_Lab
Arduino-Connection
A simple library for the connection between Unix and Arduino, with class.
ArmControllerEV3
Controller API for Taco Motors
daddabarba's Repositories
daddabarba/gym-miniworld
Simple 3D interior simulator for RL & robotics research
daddabarba/CV2_3
daddabarba/RaceGame
A modified verions of the Baum-Welch algorithm to learn Hidden Options from imitation. A simplified driving simulation is included.
daddabarba/gym-maze
A basic 2D maze environment where an agent start from the top left corner and try to find its way to the bottom left corner.
daddabarba/ToMCT
Theory of Mind agents (generic level) playing in a Colored Trails task
daddabarba/remoteShell
daddabarba/HSRRL
A reinforcement learning reactive framework for c++. It should make easier to use and test RL algorithms, including hierarchical reinforcement learning ones, such as Option Learning, and reward abstraction via Expectation Gradient
daddabarba/CPP_SocketWrapper
C++ wrapper for Server/Client TCP Sockets
daddabarba/NHRL
An adaptive algorithm, which should abstract temporally extended actions online, without the need for additional background information (besides a Markovian description of the environment). Several Reinforcement Learning algorithms where embedded in a Hierarchy of policies, among which n-step QL, Expected Sarsa, LSTM neural networks (for Q value learning), Deep Mind's Deep Q-learning architecture, and simultaneous off-policy training (of all abstract actions).
daddabarba/shell
A c shell with piping, background processes, and string parsing
daddabarba/ArmControllerEV3
Controller API for Taco Motors
daddabarba/AP_Lab
daddabarba/PID_Study
daddabarba/SpamClassifier
daddabarba/react_test
daddabarba/grasp
Controller for robotic manipulator (6 DOF). The systems uses HOG and Support Vector Machines to classify an object's position and determine how to grasp it.
daddabarba/CG_assignments
daddabarba/COURSERA-MachineLearning
daddabarba/ReproducingNestLearningThermostatAlgorithm
An algorithm that uses Polynomial Regression to reproduce the main function of the nest Thermostat , learning your daily scheldue
daddabarba/Arduino-Connection
A simple library for the connection between Unix and Arduino, with class.
daddabarba/Twistory