Kinal Mehta's repositories
Reinforcement-Learning-Notebooks
Single notebook implementation of Deep RL algorithms
Imitation-Learning-Pytorch
Imitation learning on MuJoCo Environments.
epymarl_spectral
This is the official implementation of "Effects of Spectral Normalization in Multi-agent Reinforcement Learning" accepted at IJCNN-2023
Deep-Reinforcement-Learning
Deep RL algorithms implemented on Unity Environments. Part of DRLND
deeplearning.ai-5-Course-Specialization
This repo consists of the work and assignments I worked on for the Deep Learning Specialization by Andrew Ng
kinalmehta
Github Home
Gymnasium
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
kinalmehta.github.io
Personal Site
logseq-highlighters
More highlight colors in Logseq
marl-lipo
Official codebase for Generating Diverse Cooperative Agents by Learning Incompatible Policies (notable-top-25% @ ICLR 2023)
meltingpot
A suite of test scenarios for multi-agent reinforcement learning.
Metaworld
Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning
Neural-Style-Transfer
Neural style transfer
old-website
Personal Site
sequential_social_dilemma_games
Repo for reproduction of sequential social dilemmas
smac
SMAC: The StarCraft Multi-Agent Challenge
Soft-Computing
Matlab codes of the first machine learning course I took at university.
Udacity-DLND-workspace
It contains the assignments and project works I completed during the DLND course.