NishanthJKumar
PhD with the MIT @Learning-and-Intelligent-Systems group working on AI/ML/Robotics!
MITCambridge, MA
Pinned Repositories
predicators
SeSaMe TAMP + Learning integrated with a Spot robot!
simple_rl
A simple framework for experimenting with Reinforcement Learning in Python.
predicators
Learning for effective and efficient bilevel planning
predicators_behavior
Learning for effective and efficient bilevel planning; integrated with BEHAVIOR and iGibson
airobot_reward_densification
A repository with a simple robotic domain in which to test out ideas for automatic reward densification.
fetch-block-construction
Environment codebase for ICRA 2020 paper "Towards Practical Multi-object Manipulation using Relational Reinforcement Learning"
Nishanth-Minimal-Mistakes-Customized
My repository for a barebones version of my personal website. Start here if you'd like your own website to look similar!
NishanthJKumar.github.io
GitHub repo for my personal website: https://nishanthjkumar.com
skills-to-symbols
reimplementing original work for understanding + modification!
PGMax
Loopy belief propagation for factor graphs on discrete variables, in JAX!
NishanthJKumar's Repositories
NishanthJKumar/airobot_reward_densification
A repository with a simple robotic domain in which to test out ideas for automatic reward densification.
NishanthJKumar/fetch-block-construction
Environment codebase for ICRA 2020 paper "Towards Practical Multi-object Manipulation using Relational Reinforcement Learning"
NishanthJKumar/Nishanth-Minimal-Mistakes-Customized
My repository for a barebones version of my personal website. Start here if you'd like your own website to look similar!
NishanthJKumar/NishanthJKumar.github.io
GitHub repo for my personal website: https://nishanthjkumar.com
NishanthJKumar/skills-to-symbols
reimplementing original work for understanding + modification!
NishanthJKumar/APMDP-RDDL-domains
RDDL domains for APMDP paper by Oh et. al, pubished at RSS 2019
NishanthJKumar/awesome-jax
JAX - A curated list of resources https://github.com/google/jax
NishanthJKumar/bddl
NishanthJKumar/ees.github.io
Practice Makes Perfect: Planning to Learn Skill Parameter Policies - Website
NishanthJKumar/generative-query-network-pytorch
Generative Query Network (GQN) in PyTorch as described in "Neural Scene Representation and Rendering"
NishanthJKumar/grfp
LaTeX template for the NSF Graduate Research Fellowship Program (GRFP) application.
NishanthJKumar/gripper-painting-pddl
A simple variant to the classic Gripper domain for PDDL
NishanthJKumar/Gymnasium-Robotics
A collection of robotics simulation environments for reinforcement learning
NishanthJKumar/I-DRAGGN_ReImp
A reimplementation of the I-DRAGGN model from Karamcheti et. al (2017) in an effort to make myself more fluent with PyTorch
NishanthJKumar/iGibson
A Simulation Environment to train Robots in Large Realistic Interactive Scenes
NishanthJKumar/jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
NishanthJKumar/LearningRL
This is the home of all my attempts to experiment with Reinforcement, Deep Learning and AI!
NishanthJKumar/lisdf
A repository for a universal I/O spec for TAMP, along with scripts to convert from popular specs to our spec
NishanthJKumar/pbrspot
Pybullet for Robot Motion Planning and Simulation with the Spot
NishanthJKumar/PGMax
Loopy belief propagation for factor graphs on discrete variables, in JAX!
NishanthJKumar/RLBench
A large-scale benchmark and learning environment.
NishanthJKumar/rlkit-relational
Codebase for ICRA 2020 paper "Towards Practical Multi-object Manipulation using Relational Reinforcement Learning"
NishanthJKumar/sco
Sequential Convex Optimization for TAMP problems with multiple backend solvers!
NishanthJKumar/sco_gurobi
Sequential Convex Optimization using Gurobi on the backend
NishanthJKumar/sco_OSQP
A version of the sco library for sequential convex optimization that uses the OSQP solver on the backend
NishanthJKumar/simple_rl
A simple framework for experimenting with Reinforcement Learning in Python.
NishanthJKumar/tamp-operator-learning.github.io
Website for operator learning for bilevel planning paper
NishanthJKumar/The-Hands-Free-Mouse
This is a project seeking to create an HID mouse that does not require any hand movement to work.
NishanthJKumar/UdacityDeepLearning
Repository where I maintain my solutions to the Udacity Deep Learning course along with any additional things I choose to do as part of learning the material.