Browse press releases
The newest releases come first, each with its full text here and a link to its original. Try the filters to narrow them down.
- OpenAISome considerations on learning to explore via meta-reinforcement learningCompanies: OpenAIOpenAI Abstract We consider the problem of exploration in meta reinforcement learning. Two new meta reinforcement learning algorithms are suggested: E-MAML and E-RL². Results are presented on a novel environment we call "Krazy World" and a set of maze environments. We show E-MAML and E-RL² deliver better performance on tasks where exploration is important. Learning Paradigms Authors Bradly Stadie, Ge Yang, Rein Houth
- OpenAIMulti-Goal Reinforcement Learning: Challenging robotics environments and request for researchCompanies: OpenAIOpenAI Abstract The purpose of this technical report is two-fold. First of all, it introduces a suite of challenging continuous control tasks (integrated with OpenAI Gym) based on currently existing robotics hardware. The tasks include pushing, sliding and pick & place with a Fetch robotic arm as well as in-hand object manipulation with a Shadow Dexterous Hand. All tasks have sparse binary rewards and follow a Multi-
- OpenAIInterpretable machine learning through teachingCompanies: OpenAIWe’ve designed a method that encourages AIs to teach each other with examples that also make sense to humans. Our approach automatically selects the most informative examples to teach a concept—for instance, the best images to describe the concept of dogs—and experimentally we found our approach to be effective at teaching both AIs
- OpenAIRequests for Research 2.0Companies: OpenAIWe’re releasing a new batch of seven unsolved problems which have come up in the course of our research at OpenAI.
- OpenAILearning sparse neural networks through L₀ regularizationCompanies: OpenAIAbstract We propose a practical method for L₀ norm regularization for neural networks: pruning the network during training by encouraging weights to become exactly zero. Such regularization is interesting since (1) it can greatly speed up training and inference, and (2) it can improve generalization. AIC and BIC, well-known model selection criteria, are special cases of L₀ regularization. However, since the L₀ norm o
- AdobeIntersection of Creativity and Technology Key to Success of India's Gen Z Students, Finds New Adobe StudyCompanies: AdobeToday, Adobe India released the findings of 'Gen Z in the Classroom: Creating the Future', a study aimed at providing insights into student and...
- OpenAIInterpretable and pedagogical examplesCompanies: OpenAIAbstract Teachers intentionally pick the most informative examples to show their students. However, if the teacher and student are neural networks, the examples that the teacher network learns to give, although effective at teaching the student, are typically uninterpretable. We show that training the student and teacher iteratively, rather than jointly, can produce interpretable teaching strategies. We evaluate inte
- OpenAILearning a hierarchyCompanies: OpenAIWe’ve developed a hierarchical reinforcement learning algorithm that learns high-level actions useful for solving a range of tasks, allowing fast solving of tasks requiring thousands of timesteps. Our algorithm, when applied to a set of navigation problems, discovers a set of high-level actions for walking and crawling in different directions, which enables the agent to master new navigation tasks quickly.
- OpenAIAsymmetric actor critic for image-based robot learningCompanies: OpenAIAbstract Deep reinforcement learning (RL) has proven a powerful technique in many sequential decision making domains. However, Robotics poses many challenges for RL, most notably training on a physical system can be expensive and dangerous, which has sparked significant interest in learning control policies using a physics simulator. While several recent works have shown promising results in transferring policies tra
- OpenAIDomain randomization and generative models for robotic graspingCompanies: OpenAIAbstract Deep learning-based robotic grasping has made significant progress thanks to algorithmic improvements and increased data availability. However, state-of-the-art models are often trained on as few as hundreds or thousands of unique object instances, and as a result generalization can be a challenge. In this work, we explore a novel data generation pipeline for training a deep neural network to perform grasp p
- OpenAIMeta-learning for wrestlingCompanies: OpenAIWe show that for the task of simulated robot wrestling, a meta-learning agent can learn to quickly defeat a stronger non-meta-learning agent, and also show that the meta-learning agent can adapt to physical malfunction.
- OpenAILearning to model other mindsCompanies: OpenAIWe’re releasing an algorithm which accounts for the fact that other agents are learning too, and discovers self-interested yet collaborative strategies like tit-for-tat in the iterated prisoner’s dilemma. This algorithm, Learning with Opponent-Learning Awareness (LOLA), is a small step towards agents that model other minds.