Difference between revisions of "OpenAI"
m (→OpenAI Gym and Universe) |
m |
||
| Line 9: | Line 9: | ||
* [http://openai.com/ OpenAI] | * [http://openai.com/ OpenAI] | ||
| + | * [http://openai.com/projects/five/ OpenAI Five] ...using the multiplayer video game Dota 2 as a research platform for general-purpose AI systems. ...[http://www.dota2.com/play/ Dota 2] | ||
| + | * [http://blog.openai.com/openai-charter/ Charter] | ||
* [[Reinforcement Learning (RL)]] | * [[Reinforcement Learning (RL)]] | ||
* [[Distributed Deep Reinforcement Learning (DDRL)]] | * [[Distributed Deep Reinforcement Learning (DDRL)]] | ||
| − | + | * [http://towardsdatascience.com/too-powerful-nlp-model-generative-pre-training-2-4cc6afb6655 GPT-2 - Too powerful NLP model (GPT-2) | Edward Ma - Towards Data Science] | |
= <span id="OpenAI Gym"></span>OpenAI Gym = | = <span id="OpenAI Gym"></span>OpenAI Gym = | ||
Revision as of 14:11, 15 August 2020
Youtube search... ...Google search
- OpenAI
- OpenAI Five ...using the multiplayer video game Dota 2 as a research platform for general-purpose AI systems. ...Dota 2
- Charter
- Reinforcement Learning (RL)
- Distributed Deep Reinforcement Learning (DDRL)
- GPT-2 - Too powerful NLP model (GPT-2) | Edward Ma - Towards Data Science
OpenAI Gym
OpenAI Gym and Universe
