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.
- 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.
- OpenAILearning with opponent-learning awarenessCompanies: OpenAIAbstract Multi-agent settings are quickly gathering importance in machine learning. This includes a plethora of recent work on deep multi-agent reinforcement learning, but also can be extended to hierarchical RL, generative adversarial networks and decentralised optimisation. In all these settings the presence of multiple learning agents renders the training problem non-stationary and often leads to unstable training
- OpenAIOpenAI Baselines: ACKTR & A2CCompanies: OpenAIWe’re releasing two new OpenAI Baselines implementations: ACKTR and A2C. A2C is a synchronous, deterministic variant of Asynchronous Advantage Actor Critic (A3C) which we’ve found gives equal performance. ACKTR is a more sample-efficient reinforcement learning algorithm than TRPO and A2C, and requires only slightly more computation than A2C per update.
- OpenAIMore on Dota 2Companies: OpenAIOur Dota 2 result shows that self-play can catapult the performance of machine learning systems from far below human level to superhuman, given sufficient compute. In the span of a month, our system went from barely matching a high-ranked player to beating the top pros and has continued to improve since then. Supervised deep learning systems can only be as good as their training datasets, but in self-play systems, the available data improves automatically as the agent gets better.
- OpenAIDota 2Companies: OpenAIWe’ve created a bot which beats the world’s top professionals at 1v1 matches of Dota 2 under standard tournament rules. The bot learned the game from scratch by self-play, and does not use imitation learning or tree search. This is a step towards building AI systems which accomplish well-defined goals in messy, complicated situations involving real humans.
- OpenAIGathering human feedbackCompanies: OpenAIRL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than hand-crafted reward functions. The underlying technique was developed as a step towards safe AI systems, but also applies to reinforcement learning problems with rewards that are hard to specify.
- OpenAIBetter exploration with parameter noiseCompanies: OpenAIWe’ve found that adding adaptive noise to the parameters of reinforcement learning algorithms frequently boosts performance. This exploration method is simple to implement and very rarely decreases performance, so it’s worth trying on any problem.
- OpenAIProximal Policy OptimizationCompanies: OpenAIWe’re releasing a new class of reinforcement learning algorithms, Proximal Policy Optimization (PPO), which perform comparably or better than state-of-the-art approaches while being much simpler to implement and tune. PPO has become the default reinforcement learning algorithm at OpenAI because of its ease of use and good performance.
- OpenAIHindsight Experience ReplayCompanies: OpenAIAbstract Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering. It can be combined with an arbitrary off-policy RL algorithm and may be seen as a form of implicit curriculum
- OpenAITeacher–student curriculum learningCompanies: OpenAIOpenAI Abstract We propose Teacher–Student Curriculum Learning (TSCL), a framework for automatic curriculum learning, where the Student tries to learn a complex task and the Teacher automatically chooses subtasks from a given set for the Student to train on. We describe a family of Teacher algorithms that rely on the intuition that the Student should practice more those tasks on which it makes the fastest progress, i
- OpenAILearning from human preferencesCompanies: OpenAIOne step towards building safe AI systems is to remove the need for humans to write goal functions, since using a simple proxy for a complex goal, or getting the complex goal a bit wrong, can lead to undesirable and even dangerous behavior. In collaboration with DeepMind’s safety team, we’ve developed an algorithm which can infer what humans want by being told which of two proposed behaviors is better.
- OpenAILearning to cooperate, compete, and communicateCompanies: OpenAIMultiagent environments where agents compete for resources are stepping stones on the path to AGI. Multiagent environments have two useful properties: first, there is a natural curriculum—the difficulty of the environment is determined by the skill of your competitors (and if you’re competing against clones of yourself, the environment exactly matches your skill level). Second, a multiagent environment has no stable equilibrium: no matter how smart an agent is, there’s always pressure to get smarter. These environments have a very different feel from traditional environments, and it’ll take a lot more research before we become good at them.