Tanmay Shankar

RCNN_MDP. Code base for solving Markov Decision Processes and Reinforcement Learning problems using Recurrent Convolutional Neural Networks.

AIR_papers. Database of Artificial Intelligence and Robotics papers.

ParsingbyImitation. Codebase for sequentially selecting primitives and their respective goal locations via Deep Reinforcement Learning

CausalSkillLearning. Codebase for project about unsupervised skill learning via variational inference and causality.

decision_making. Code base for inverse reinforcement learning through demonstrations for a ground robot.

DeepVectorPolicyFields. Codebase for learning Vector Policy Fields using Reinforcement Learning Networks.

ActionPrimitives. Codebase for implementing Dynamical Movement Primitives.

DiscoverMotorPrograms. Cleaned up codebase for motor programs.

DeepBelief. Codebase for Deep Belief Space Networks

Visualize_Primitives. Codebase for Visualization of ActionPrimitives.

website. Jupyter Notebook

hand_dapg. Repository to accompany RSS 2018 paper on dexterous hand manipulation