🕐 --:--
-- --
عاجل
⚡ عاجل: كريستيانو رونالدو يُتوّج كأفضل لاعب كرة قدم في العالم ⚡ أخبار عاجلة تتابعونها لحظة بلحظة على خبر ⚡ تابعوا آخر المستجدات والأحداث من حول العالم
⌘K
AI مباشر | -- مشاهد مباشر
842,925 مقال 403 مصدر نشط 224 قناة مباشرة 5,082 خبر اليوم
آخر تحديث: منذ 0 ثانية
الفلاتر: 🏷️ tech مسح الكل ✕

Generalizing from simulation

Our latest robotics techniques allow robot controllers, trained entirely in simulation and deployed on physical robots, to react to unplanned changes in the environment as they solve simple tasks. That is, we’ve used these techniques to build closed-loop systems rather than open-loop ones as before.

OpenAI Blog تكنولوجيا منذ 8 سنوات

Generalizing from simulation

Our latest robotics techniques allow robot controllers, trained entirely in simulation and deployed on physical robots, to react to unplanned changes in the environment as they solve simple tasks. That is, we’ve used these techniques to build closed-loop systems rather than open-loop ones as before.

OpenAI Blog تكنولوجيا منذ 8 سنوات

Meta-learning for wrestling

We 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.

OpenAI Blog تكنولوجيا منذ 8 سنوات

Meta-learning for wrestling

We 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.

OpenAI Blog تكنولوجيا منذ 8 سنوات

Competitive self-play

We’ve found that self-play allows simulated AIs to discover physical skills like tackling, ducking, faking, kicking, catching, and diving for the ball, without explicitly designing an environment with these skills in mind. Self-play ensures that the environment is always the right difficulty for an AI to improve. Taken alongside our Dota 2 self-play results, we have increasing confidence that self-play will be a core part of powerful AI systems in the future.

OpenAI Blog تكنولوجيا منذ 8 سنوات

Competitive self-play

We’ve found that self-play allows simulated AIs to discover physical skills like tackling, ducking, faking, kicking, catching, and diving for the ball, without explicitly designing an environment with these skills in mind. Self-play ensures that the environment is always the right difficulty for an AI to improve. Taken alongside our Dota 2 self-play results, we have increasing confidence that self-play will be a core part of powerful AI systems in the future.

OpenAI Blog تكنولوجيا منذ 8 سنوات

Measure Brand Lift Across TV and Facebook - meta.com

Measure Brand Lift Across TV and Facebook  meta.com

Meta Newsroom تكنولوجيا منذ 8 سنوات

Contact - Tesla

Contact  Tesla

Tesla News تكنولوجيا منذ 8 سنوات

Find Us - Tesla

Find Us  Tesla

Tesla News تكنولوجيا منذ 8 سنوات

Supercharger - Tesla

Supercharger  Tesla

Tesla News تكنولوجيا منذ 8 سنوات

Announcing New Ways to Enjoy Memories with Friends - meta.com

Announcing New Ways to Enjoy Memories with Friends  meta.com

Meta Newsroom تكنولوجيا منذ 8 سنوات

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 Blog تكنولوجيا منذ 8 سنوات

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 Blog تكنولوجيا منذ 8 سنوات

Hard Questions: What Should Happen to People’s Online Identity When They Die? - meta.com

Hard Questions: What Should Happen to People’s Online Identity When They Die?  meta.com

Meta Newsroom تكنولوجيا منذ 8 سنوات

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.

OpenAI Blog تكنولوجيا منذ 8 سنوات

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.

OpenAI Blog تكنولوجيا منذ 8 سنوات

Marketplace Expanding to Europe - meta.com

Marketplace Expanding to Europe  meta.com

Meta Newsroom تكنولوجيا منذ 8 سنوات

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.

OpenAI Blog تكنولوجيا منذ 8 سنوات

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.

OpenAI Blog تكنولوجيا منذ 8 سنوات

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.

OpenAI Blog تكنولوجيا منذ 8 سنوات
AI
يا هلا! اسألني أي شي 🎤
FREE Free 1GB Internet + Free International Calls

$1 trial — eSIM in 190+ countries — No roaming charges

Download Free
🔍