anishhdiwan
Graduate student in robotics @ TU Delft. Interested in fields of reinforcement learning, imitation learning, deep learning, and multi-agent systems
Pinned Repositories
DQfD_Minecraft
This repo contains code and documentation to train a DQfD agent to solve the Treechop environment in mineRL v0.4
NonHolonomicRRT_PDM
Implementation of a RRT algorithm for a non-holonomic parking robot, created for the course Planning & Decision Making (RO47005) at the Technische Universiteit Delft
symbolic_dqn
This repository documents an approach to neural-guided population initialisation for genetic programming (symbolic regression) through the Deep Q-Networks algorithm.
am-i-done
This repository contains code for reproduction and subsequent analysis of the paper titled "Am I done? Predicting action progress in videos". This reproduction is carried out as part of a course project for the course Deep Learning.
py_road_rash
Self driving vehicle in the 1995 game Road Rash
differentiable_GP_lunarlander
Evolving a differentiable genetic programming algorithm to solve the openAI gym lunar lander environment
distill_template
This repo contains the Distill Pub V1 template and some related files used to make my personal website
DMP_baselines
Baselines and comparison algorithms for background work on "Learning Cost Functions From Demonstrations for Contact-Rich Robot Manipulation"
motion_ncsn
Noise Conditional Score Networks (NeurIPS 2019, Oral) modified for trajectories of imitation learning demonstration motions
near
Imitation Learning from Observation Through Generative Modelling
anishhdiwan's Repositories
anishhdiwan/near
Imitation Learning from Observation Through Generative Modelling
anishhdiwan/motion_ncsn
Noise Conditional Score Networks (NeurIPS 2019, Oral) modified for trajectories of imitation learning demonstration motions
anishhdiwan/pomdp-py
A framework to build and solve POMDP problems. Documentation: https://h2r.github.io/pomdp-py/
anishhdiwan/DMP_baselines
Baselines and comparison algorithms for background work on "Learning Cost Functions From Demonstrations for Contact-Rich Robot Manipulation"
anishhdiwan/paperplots
Camera ready machine learning plots and figures with a Tensorboard-like API
anishhdiwan/wix_mathjax_tutorial
How to add MathJax math equations to Wix
anishhdiwan/recursive_beliefs
anishhdiwan/symbolic_dqn
This repository documents an approach to neural-guided population initialisation for genetic programming (symbolic regression) through the Deep Q-Networks algorithm.
anishhdiwan/differentiable_GP_lunarlander
Evolving a differentiable genetic programming algorithm to solve the openAI gym lunar lander environment
anishhdiwan/DQfD_Minecraft
This repo contains code and documentation to train a DQfD agent to solve the Treechop environment in mineRL v0.4
anishhdiwan/am-i-done
This repository contains code for reproduction and subsequent analysis of the paper titled "Am I done? Predicting action progress in videos". This reproduction is carried out as part of a course project for the course Deep Learning.
anishhdiwan/py_road_rash
Self driving vehicle in the 1995 game Road Rash
anishhdiwan/distill_template
This repo contains the Distill Pub V1 template and some related files used to make my personal website