2101

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.

2102

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.

2103

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.

2104

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.

2105

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.

2106

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.

2107

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.

2108

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.

2109

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.

2110

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.

2111

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.

2112

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.

2113

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.

2114

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.

2115

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.

2116

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.

2117

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.

2118

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.

2119

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.

2120

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.

2121

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.

2122

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.

2123

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.

2124

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.

2125

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.

2126

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.

2127

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.

2128

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.

2129

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.

2130

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.

2131

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.

2132

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.

2133

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.

2134

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.

2135

OpenAI Learning with Opponent-Learning Awareness (LOLA)

OpenAI introduces Learning with Opponent-Learning Awareness (LOLA), a multi-agent reinforcement learning method that enables agents to shape the learning of other agents to foster cooperation and reach Nash equilibrium.

2136

OpenAI Baselines: ACKTR & A2C

OpenAI has released Baselines implementations of ACKTR and A2C, providing a more sample-efficient reinforcement learning algorithm (ACKTR) and a synchronous, deterministic variant of A3C (A2C).

2137

OpenAI Dota 2 1v1 Bot Results

OpenAI developed a reinforcement learning agent that achieved superhuman performance in Dota 2 1v1, demonstrating that self-play can scale machine learning systems beyond human-level capability.

2138

OpenAI Dota 2 Bot Announcement

OpenAI has developed a bot capable of defeating top professional Dota 2 players in 1v1 matches using self-play reinforcement learning without imitation learning or tree search.

2139

OpenAI RL-Teacher Release

OpenAI has released RL-Teacher, an open-source interface that allows AI agents to be trained via occasional human feedback instead of hand-crafted reward functions.

2140

OpenAI Better Exploration with Parameter Noise

OpenAI introduces a method of adding adaptive noise to neural network parameters rather than the action space, significantly boosting reinforcement learning performance and exploration consistency.

2141

Proximal Policy Optimization (PPO) Release Notes – OpenAI Baselines

OpenAI released Proximal Policy Optimization (PPO), a simple-to-implement reinforcement learning algorithm that matches or exceeds state-of-the-art performance while becoming the default RL method at OpenAI.

2142

OpenAI Robust Adversarial Inputs Research

OpenAI has developed images that remain adversarial across varied scales and perspectives, challenging the notion that multi-perspective image capture in systems like self-driving cars prevents malicious trickery.

2143

OpenAI Hindsight Experience Replay

OpenAI introduced Hindsight Experience Replay, a technique that enables sample-efficient reinforcement learning from sparse, binary rewards by treating failed attempts as successful achievements of alternative goals.

2144

OpenAI Teacher–Student Curriculum Learning

OpenAI introduces Teacher–Student Curriculum Learning (TSCL), an automatic framework that optimizes training by selecting subtasks based on the student's learning progress and performance decay.

2145

mujoco-py 1.50.1.0 release notes / what's new

OpenAI has open-sourced mujoco-py 1.50.1.0, a high-performance Python 3 binding for the MuJoCo engine that introduces batched simulation and GPU-accelerated rendering.

2146

OpenAI Learning from Human Preferences

OpenAI and DeepMind developed a reinforcement learning algorithm that infers goals from human preference comparisons, reducing the need for manually written reward functions.

2147

OpenAI MADDPG: Learning to Cooperate, Compete, and Communicate

OpenAI introduced MADDPG, a reinforcement learning algorithm that uses centralized learning and decentralized execution to enable multiple agents to collaborate and compete in complex environments.

2148

OpenAI UCB Exploration via Q-Ensembles

OpenAI researchers developed an exploration strategy using an ensemble of Q*-functions based on Upper-Confidence Bounds (UCB) to improve deep reinforcement learning performance on Atari benchmarks.

2149

OpenAI Baselines: DQN release and reinforcement learning best practices

OpenAI has open-sourced OpenAI Baselines, starting with a high-performance implementation of DQN and three of its variants to improve reproducibility in reinforcement learning.

2150

OpenAI Robots That Learn: One-Shot Imitation Learning from Simulation

OpenAI has developed a robotics system trained entirely in simulation that can learn new tasks from a single human demonstration provided via VR.