- Why is DeepMinds AlphaZero learning chess/go from scratch a bigger deal than OpenAI learning DOTA from scratch? https://blog.openai.com/dota-2/ 16 comments artificial
- Elon Musk's OpenAI first ever to defeat world's best players in competitive DotA 2 https://blog.openai.com/dota-2/ 33 comments worldnews
- OpenAI bot defeats top Dota 2 player Dendi at The International https://blog.openai.com/dota-2/ 26 comments technology
- OpenAI: human-level 1v1 micro DotA play via self-play deep RL; tournament demonstration https://blog.openai.com/dota-2/ 11 comments reinforcementlearning
Linking pages
- AI winter is well on its way – Piekniewski's blog https://blog.piekniewski.info/2018/05/28/ai-winter-is-well-on-its-way/ 939 comments
- OpenAI Five Benchmark https://blog.openai.com/openai-five-benchmark 94 comments
- Deep Reinforcement Learning Doesn't Work Yet https://www.alexirpan.com/2018/02/14/rl-hard.html 90 comments
- Reinforcement learning’s foundational flaw https://thegradient.pub/why-rl-is-flawed/ 55 comments
- Fairness in Man vs. Machine Competitions http://fuzyll.com/2017/fairness-in-man-vs-machine-competitions/ 37 comments
- More on Dota 2 https://blog.openai.com/more-on-dota-2/?%21= 33 comments
- Counterfactual Regret Minimization - the core of Poker AI beating professional players int8.io https://int8.io/counterfactual-regret-minimization-for-poker-ai/ 32 comments
- Reinforcement Learning from scratch | by Emmanuel Ameisen | Insight https://blog.insightdatascience.com/reinforcement-learning-from-scratch-819b65f074d8 25 comments
- AI Safety via Debate https://blog.openai.com/debate/ 17 comments
- How AI Training Scales https://blog.openai.com/science-of-ai/ 15 comments
- People are far more likely to be killed by artificial intelligence than nuclear war with North Korea, warns Elon Musk | The Independent | The Independent http://www.independent.co.uk/life-style/gadgets-and-tech/news/ai-north-korea-nuclear-war-elon-musk-tesla-artificial-intelligence-robots-a7892066.html 11 comments
- AI in 2018 for researchers. Ciao everyone! 2017 was one of the most… | by Alex Honchar | Good Audience http://medium.com/@alexrachnog/ai-in-2018-for-researchers-8955df0caaf9 0 comments
- AI in 2018 for researchers. Ciao everyone! 2017 was one of the most… | by Alex Honchar | Good Audience https://blog.goodaudience.com/ai-in-2018-for-researchers-8955df0caaf9 0 comments
- 30 Under 30 In Enterprise Tech: Reinventing Business With Artificial Intelligence https://www.forbes.com/sites/helenpopkin/2017/11/14/ai-outsourcing-self-driving-cars-and-serving-the-weed-industry-30-under-30-in-enterprise-tech/#2b571e365959 0 comments
- For AI, the Real World Is Harder Than Gaming - The Atlantic https://www.theatlantic.com/technology/archive/2018/02/ai-keeps-mastering-games-but-can-it-win-in-the-real-world/554312/?single_page=true 0 comments
- Deep Reinforcement Learning http://planspace.org/20171114-deep_rl/ 0 comments
- Scalable agent alignment via reward modeling | by DeepMind Safety Research | Medium https://medium.com/@deepmindsafetyresearch/scalable-agent-alignment-via-reward-modeling-bf4ab06dfd84 0 comments
- Counterfactual Regret Minimization - the core of Poker AI beating professional players int8.io https://int8.io/counterfactual-regret-minimization-for-poker-ai/?href= 0 comments
- Understanding OpenAI Five. How to teach a pigeon cool tricks | by Evan Pu | Medium https://medium.com/@evanthebouncy/understanding-openai-five-16f8d177a957 0 comments