Ablation Study of the Bayesian GAN
Exploring the capacity and limitation of the Bayesian GAN.
Generating Gaussian Samples From A Uniform Distribution
Generating numbers that are distributed with the Gaussian distribution (with any mean and standard deviation as parameters), starting from the random number generator of a computer, i.e. the rand() function.
Distributional Reinforcement Learning
Presenting some of the most fundamental works on distributional RL.
Actor-Critic with Experience Replay
A brief overview of the ACER RL algorithm is provided.
Exploration and Generalization in Reinforcement Learning
A brief description on a few methods to make RL agents explore and generalize faster/better.
Reinforcement Learning Key Papers Keynotes
Keynotes from teh RL Key Papers of Spinning Up by OpenAI.
Convolutional Neural Network Explanation Methods
A brief description on explanations methods in the computer vision literature.
Automatic Environment Generation to Generalize Agents
Using GANs and evolution algorithms to generate a curriculum for the RL agent.
RL Course by David Silver Notes
After being excited about RL for more than a year, I should have a concise and satisfying answer to the question, 'What is reinforcement learning?' Here it is gathered briefly.