Santara
Software Engineer @ Google Research | 2x Research/SWE Intern at Google Brain | Interests: Deep Learning, Reinforcement Learning, Robotics
Google ResearchKolkata, West Bengal, India
Pinned Repositories
anirban-imitation
Extension of (Generative Adversarial Imitation Learning)[https://arxiv.org/abs/1606.03476]
DeepGTAV
A plugin for GTAV that transforms it into a vision-based self-driving car development environment. It supports two main operation modes, Dataset generation or Reinforcement Learning environment and it is super easy to install!
deeptesla
End-to-End Learning from Tesla Autopilot Driving Data
DeepUserModelling
Deep learnt user model for scientific paper recommendation
e2e_ASR_Lasagne_CTC
This is IIT Kharagpur's end to end deep learnt speech recognition system
ML-MOOC-NPTEL
This repository contains the Tutorials for the NPTEL MOOC on Machine Learning.
RAIL
Codebase of Santara et. al., RAIL: Risk Averse Imitation Learning, Published in AAMAS 2018
reinforcement-learning-car
Using reinforcement learning to teach a car to avoid obstacles.
safeRL
Safe Reinforcement Learning algorithms
stochastic_value_gradient
Implementation of (Learning Continuous Control Policies by Stochastic Value Gradients)[https://arxiv.org/abs/1510.09142]
Santara's Repositories
Santara/ML-MOOC-NPTEL
This repository contains the Tutorials for the NPTEL MOOC on Machine Learning.
Santara/stochastic_value_gradient
Implementation of (Learning Continuous Control Policies by Stochastic Value Gradients)[https://arxiv.org/abs/1510.09142]
Santara/RAIL
Codebase of Santara et. al., RAIL: Risk Averse Imitation Learning, Published in AAMAS 2018
Santara/deeptesla
End-to-End Learning from Tesla Autopilot Driving Data
Santara/e2e_ASR_Lasagne_CTC
This is IIT Kharagpur's end to end deep learnt speech recognition system
Santara/anirban-imitation
Extension of (Generative Adversarial Imitation Learning)[https://arxiv.org/abs/1606.03476]
Santara/reinforcement-learning-car
Using reinforcement learning to teach a car to avoid obstacles.
Santara/safeRL
Safe Reinforcement Learning algorithms
Santara/DeepGTAV
A plugin for GTAV that transforms it into a vision-based self-driving car development environment. It supports two main operation modes, Dataset generation or Reinforcement Learning environment and it is super easy to install!
Santara/self-driving-car
Self Driving Car development tools and technologies from GTA Robotics Community members
Santara/self-driving-car-sim
A self-driving car simulator built with Unity
Santara/MADRaS
Multi-Agent DRiving Simulator
Santara/minimal-mistakes
:triangular_ruler: A flexible two-column Jekyll theme. Perfect for personal sites, blogs, and portfolios hosted on GitHub or your own server.
Santara/models
Models built with TensorFlow
Santara/self-driving-car-1
The Udacity open source self-driving car project
Santara/SENet
Squeeze-and-Excitation Networks
Santara/AirSim
Open source simulator based on Unreal Engine for autonomous vehicles from Microsoft AI & Research
Santara/autoSLR
Automated Systematic Literature Review
Santara/Autoware
Open-source software for urban autonomous driving
Santara/baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
Santara/CarND-Behavioral-Cloning-P3
Starting files for the CarND behavioral cloning project (P3)
Santara/DeepRL-Agents
A set of Deep Reinforcement Learning Agents implemented in Tensorflow.
Santara/grad-cam.tensorflow
Implementation of Grad CAM in tensorflow
Santara/HSISeg
Santara/neurojs
A javascript deep learning and reinforcement learning library.
Santara/SafeMDP
Safe exploration in Markov Decision Processes
Santara/simple_dqn
Simple deep Q-learning agent.
Santara/tf_metrics
Multi-class metrics for Tensorflow
Santara/third_person_im
third person imitation learning shit post for replication
Santara/universe-windows-envs
Run Universe environments in Windows (maintained by DeepDrive)