AI
OpenAI Baselines: ACKTR & A2C
OpenAI has released two new implementations of its Baselines library: ACKTR and A2C. A2C is a version of Asynchronous Advantage Actor Critic (A3C) tha...
AI
AI
More on Dota 2
Researchers from OpenAI have achieved a significant breakthrough in machine learning by using self-play to improve the performance of their system. Th...
AI
Dota 2
OpenAI has created a Dota 2 bot that can beat top professionals at 1v1 matches under standard tournament rules. The bot learned the game from scratch ...
AI
Gathering human feedback
RL-Teacher is an open-source tool for training AIs using occasional human feedback instead of pre-defined reward functions. This approach aims to impr...
AI
How to Explain the Prediction of a Machine Learning Model?
Machine learning models are increasingly being used in critical areas like healthcare, justice systems, and finance. However, their predictions can be...
AI
Better exploration with parameter noise
Researchers at OpenAI have discovered that adding adaptive noise to the parameters of reinforcement learning algorithms can improve performance. This ...
AI
Predict Stock Prices Using RNN: Part 2
A tutorial on using Recurrent Neural Networks (RNNs) to predict stock prices continues from Part 1. The author adds the ability for the RNN to respond...
AI
Proximal Policy Optimization
OpenAI has developed a new class of reinforcement learning algorithms called Proximal Policy Optimization (PPO). These algorithms are simpler to imple...
AI
Robust adversarial inputs
Researchers at OpenAI have created images that consistently fool neural network classifiers when viewed from different scales and perspectives. This f...
AI
Predict Stock Prices Using RNN: Part 1
A tutorial on building a recurrent neural network (RNN) using TensorFlow to predict stock market prices. The author provides a step-by-step guide and ...
AI
Hindsight Experience Replay
Hindsight Experience Replay (HER) is a reinforcement learning algorithm that allows agents to learn from past experiences, even if the desired outcome...
AI
Teacher–student curriculum learning
Researchers at OpenAI have proposed a new method for training AI models called teacher-student curriculum learning. This approach involves creating a ...