Deep Reinforcement Learning on Lunar Lander gym environment

Navigation project of Udacity Deep Reinforcement Learning

An Optimistic Approach to the Q-Network Error in Actor-Critic Methods

Safe and Robust Experience Sharing for Deterministic Policy Gradient Algorithms

Towards Rehearsal-based Continual Learning at Scale: distributed CL with Horovod + PyTorch

Tackling continual learning as part of a project for university

Deep convolutional Q-Learning project powered by Gym

XARL: Explanation-Aware Reinforcement Learning

Distributed RL platform with modified IMPALA architecture. Implements CLEAR, LASER V-trace modifications along with Attentive and Elite sampling experience replay methods.

Policy-Based Methods. Learn the theory behind evolutionary algorithms and policy-gradient methods. Design your own algorithm to train a simulated robotic arm to reach target locations.

A Reinforcement Learning library for solving custom environments

Lunar Lander training using Deep-Q-Learning

Reinforcement learning of point to point reaching

Value-based methods. Apply deep learning architectures to reinforcement learning tasks. Train your own agent that navigates a virtual world from sensory data.

Implementation reinforcement learning algorithms

Udacity Deep Reinforcement Learning Nanodegree Program - Navigation Control

M.Sc. thesis on Continual Learning for Non-Autoregressive Neural Machine Translation

A Deep Q-Network to play Doom

This project inolved applied Reinfocrcement learnging viz,. Deep Q Learning for the 'cart' to learn to balance the 'pole'