نتائج البحث
Learning to model other minds
We’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.
Learning to model other minds
We’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.
UAE martyr Sultan Al Naqbi laid to rest in Ras Al Khaimah - Emirates 24|7
UAE martyr Sultan Al Naqbi laid to rest in Ras Al Khaimah Emirates 24|7
Learning with opponent-learning awareness
Find Us - Tesla
Find Us Tesla
Supercharger - Tesla
Supercharger Tesla
Announcing New Ways to Enjoy Memories with Friends - meta.com
Announcing New Ways to Enjoy Memories with Friends meta.com
OpenAI Baselines: ACKTR & A2C
We’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.
OpenAI Baselines: ACKTR & A2C
We’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.
More on Dota 2
Our 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.
More on Dota 2
Our 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.
Marketplace Expanding to Europe - meta.com
Marketplace Expanding to Europe meta.com
Dota 2
We’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.
Dota 2
We’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.
Gathering human feedback
RL-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.
Gathering human feedback
RL-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.
Tesla Q1 2026 Financial Results and Q&A Webcast - Tesla
Tesla Q1 2026 Financial Results and Q&A Webcast Tesla
Better exploration with parameter noise
We’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.
Better exploration with parameter noise
We’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.
Proximal Policy Optimization
We’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.