1001

OpenAI Scholars 2018 Final Projects

OpenAI published a showcase of final projects from the 2018 Scholars program, featuring diverse applications of machine learning in music generation, intuitive physics, and natural language processing.

1002

OpenAI Five: The International 2018 Results

OpenAI Five competed against world-class professional Dota 2 players at The International 2018, demonstrating high-level gameplay despite losing both matches under 'Real Dota' rules.

1003

OpenAI Large-scale Study of Curiosity-Driven Learning

OpenAI researchers demonstrated that agents trained solely on intrinsic curiosity rewards—based on prediction error—can achieve high performance across 54 benchmark environments without any hand-designed extrinsic rewards.

1004

OpenAI Five Benchmark Results

OpenAI Five won a best-of-three series against a team of 99.95th percentile Dota players, demonstrating advanced AI capabilities in handling complexity and uncertainty.

1005

OpenAI Dactyl: Learning Dexterity through Domain Randomization

OpenAI developed Dactyl, a system that trains a human-like robot hand in simulation to manipulate physical objects with high dexterity, transferring those skills to the real world without fine-tuning.

1006

OpenAI Variational Option Discovery Algorithms

OpenAI introduces Variational Autoencoding Learning of Options by Reinforcement (VALOR) and a curriculum learning approach to stabilize the discovery of diverse behavioral modes in reinforcement learning agents.

1007

OpenAI Scholars 2018: Meet our Scholars

OpenAI introduced its 2018 Scholars cohort, featuring a diverse group of researchers focusing on areas such as reinforcement learning, language modeling, and the intersection of AI and the arts.

1008

OpenAI Five Benchmark

OpenAI announced a benchmark match for OpenAI Five, featuring an expanded hero pool and updated game mechanics to test the AI against high-percentile human players.

1009

Glow: Better Reversible Generative Models

OpenAI introduces Glow, a flow-based generative model using invertible 1x1 convolutions to generate high-resolution images with exact latent-variable inference and efficient sampling.

1010

Learning Montezuma’s Revenge from a Single Demonstration

OpenAI trained an RL agent to achieve a record high score of 74,500 in Montezuma’s Revenge by using a single human demonstration to create a reverse curriculum of starting states.

1011

OpenAI Five

OpenAI Five, a team of five neural networks trained via self-play on Dota 2, began defeating amateur human teams and showed that scaled-up reinforcement learning can handle long-horizon, partially observed tasks without fundamental algorithmic advances.

1012

OpenAI Retro Contest Results

OpenAI concluded its first Retro Contest, where the top-performing AI agents for Sonic the Hedgehog were developed by tuning or extending existing algorithms like PPO and Rainbow DQN.

1013

OpenAI Learning Policy Representations in Multiagent Systems

OpenAI introduces a general learning framework that treats agent modeling as a representation learning problem to understand agent behavior in multiagent systems using minimal interaction data.

1014

OpenAI Improving Language Understanding with Unsupervised Learning

OpenAI demonstrated that a Transformer-based model pre-trained via unsupervised language modeling and then fine-tuned on small supervised datasets can achieve state-of-the-art results across diverse language tasks, including commonsense reasoning.

1015

GamePad: A learning environment for theorem proving

OpenAI introduced GamePad, a system designed to apply machine learning methods to theorem proving within the Coq proof assistant to automate tactic prediction and position evaluation.

1016

OpenAI Fellows Program Fall 2018

OpenAI launched the Fellows program in Fall 2018 to provide a pathway for individuals without formal AI backgrounds to transition into artificial intelligence research.

1017

OpenAI Gym Retro Release

OpenAI has released the full version of Gym Retro, a reinforcement learning platform that expands the available game library to over 1,000 titles across multiple classic consoles to enable research into agent generalization.

1018

OpenAI AI and Compute Analysis

OpenAI analysis reveals that compute used for the largest AI training runs has grown exponentially since 2012, doubling every 3.4 months and far outpacing Moore's Law.

1019

AI Safety via Debate

OpenAI proposes a safety technique that trains AI agents to debate topics to help humans supervise systems that perform tasks beyond human cognitive capabilities.

1020

OpenAI Evolved Policy Gradients (EPG)

OpenAI introduces Evolved Policy Gradients (EPG), a metalearning approach that evolves loss functions to help RL agents generalize to new tasks within a task family.

1021

OpenAI Gotta Learn Fast Benchmark

OpenAI has introduced a new reinforcement learning benchmark based on the Sonic the Hedgehog video game franchise to measure transfer learning and few-shot learning performance.

1022

OpenAI Retro Contest and Gym Retro Release

OpenAI launched the Retro Contest to measure reinforcement learning generalization across unseen video game levels and released Gym Retro, a platform integrating 30 SEGA Genesis and 62 Atari 2600 games into Gym.

1023

OpenAI Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines

OpenAI researchers developed a bias-free action-dependent baseline for policy gradient methods to reduce gradient estimate variance, enabling faster learning in high-dimensional action spaces.

1024

OpenAI OT-GAN: Improving GANs using optimal transport

OpenAI introduces Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets that uses a new mini-batch energy distance metric to improve training stability and image generation quality.

1025

OpenAI Hackathon Report March 2018

OpenAI hosted its first hackathon on March 3, 2018, bringing together 100 AI community members to develop projects spanning healthcare, safety, and reinforcement learning.

1026

On First-Order Meta-Learning Algorithms

OpenAI introduces Reptile, a first-order meta-learning algorithm that enables agents to learn quickly on new tasks by optimizing parameter initialization without requiring second-order derivatives.

1027

OpenAI Reptile: A Scalable Meta-Learning Algorithm

OpenAI introduced Reptile, a scalable meta-learning algorithm that enables models to generalize from a small number of examples by maximizing the inner product between gradients of different minibatches from the same task.

1028

OpenAI Scholars Program

OpenAI launched the OpenAI Scholars program to provide stipends and mentorship to individuals from underrepresented groups to study deep learning and open-source a project.

1029

OpenAI Research: Learning to Explore via Meta-Reinforcement Learning

OpenAI researchers introduced E-MAML and E-RL², two meta-reinforcement learning algorithms designed to improve exploration performance in complex environments.

1030

OpenAI Ingredients for Robotics Research

OpenAI released eight simulated robotics environments and a Baselines implementation of Hindsight Experience Replay (HER) to enable reinforcement learning from sparse rewards in complex manipulation tasks.

1031

OpenAI Multi-Goal Reinforcement Learning Robotics Environments

OpenAI has released a suite of challenging continuous control robotics tasks integrated with OpenAI Gym to advance research in Multi-Goal Reinforcement Learning.

1032

OpenAI Hackathon March 2018

OpenAI hosted a community hackathon and series of talks on March 3, 2018, in San Francisco to encourage AI learning and project development.

1033

OpenAI Supporters and Organizational Updates

OpenAI announced new donors, advisor appointments, and the departure of Elon Musk from its Board of Directors to avoid potential conflicts with Tesla's AI focus.

1034

OpenAI Preparing for Malicious Uses of AI

OpenAI and partners released a research paper forecasting how AI could be misused by malicious actors and providing recommendations for mitigating these global security threats.

1035

OpenAI Interpretable Machine Learning through Teaching

OpenAI introduces a machine teaching approach that uses a teacher-student neural network framework to identify the most illustrative examples of a concept, ensuring the resulting interpretations are human-interpretable rather than arbitrary.

1036

OpenAI Discovering Types for Entity Disambiguation

OpenAI developed a system that uses a neural network to predict membership in automatically discovered types to improve entity disambiguation accuracy on CoNLL and TAC KBP 2010 datasets.

1037

OpenAI Requests for Research 2.0

OpenAI released Requests for Research 2.0, a collection of seven unsolved technical problems in reinforcement learning and machine learning to encourage community contribution.

1038

Scaling Kubernetes to 2,500 Nodes

OpenAI describes the technical optimizations required to scale a Kubernetes cluster to 2,500 nodes on Azure for deep learning research, addressing bottlenecks in etcd, networking, and image pulls.

1039

OpenAI Block-sparse GPU Kernels

OpenAI has released highly-optimized GPU kernels for block-sparse neural network architectures, enabling models to be wider and deeper while running orders of magnitude faster than cuBLAS or cuSPARSE.

1040

OpenAI Learning Sparse Neural Networks through L0 Regularization

OpenAI introduces a method for L0 norm regularization in neural networks to create sparse models that improve training speed, inference speed, and generalization by using stochastic gates to make weights exactly zero.

1041

OpenAI Interpretable and Pedagogical Examples Research

OpenAI researchers demonstrate that training teacher and student neural networks iteratively, rather than jointly, produces interpretable teaching strategies that can effectively teach both AI and humans.

1042

OpenAI Learning a Hierarchy Research

OpenAI has developed Meta-Learning Shared Hierarchies (MLSH), a reinforcement learning algorithm that automatically discovers high-level actions to solve complex, long-horizon tasks more efficiently than brute-force methods.

1043

OpenAI Generalizing from Simulation

OpenAI developed techniques using dynamics and domain randomization to train robot controllers in simulation that can generalize to physical robots and react to unplanned environmental changes.

1044

OpenAI Sim-to-Real Transfer of Robotic Control with Dynamics Randomization

OpenAI researchers developed a dynamics randomization method that allows robotic control policies trained exclusively in simulation to transfer to real-world hardware without further physical training.

1045

OpenAI Asymmetric Actor Critic for Image-Based Robot Learning

OpenAI introduces an asymmetric actor-critic framework that improves robot learning by training the critic on full simulator states while the actor relies only on RGBD images, enabling efficient simulation-to-real transfer without real-world data.

1046

OpenAI Domain Randomization and Generative Models for Robotic Grasping

OpenAI developed a data generation pipeline using domain randomization and an autoregressive model to achieve an 80% real-world grasping success rate on unseen objects using only simulated training data.

1047

OpenAI Meta-learning for Wrestling

OpenAI demonstrated that meta-learning agents can quickly adapt their tactics to defeat stronger fixed-policy agents and recover from physical malfunctions in simulated robot wrestling.

1048

OpenAI Competitive Self-Play Research

OpenAI demonstrated that competitive self-play allows simulated 3D robots to autonomously discover complex physical skills like tackling and diving without explicit human design.

1049

Nonlinear Computation in Deep Linear Networks

OpenAI researchers discovered that deep linear networks can perform nonlinear computation by exploiting floating-point arithmetic underflow around zero.

1050

OpenAI and Oxford Introduce LOLA for Multi-Agent Reinforcement Learning

OpenAI and the University of Oxford have developed Learning with Opponent-Learning Awareness (LOLA), an RL agent that shapes the learning of other agents to achieve mutually beneficial outcomes.