Difference between revisions of "OpenAI"
m |
m |
||
| Line 16: | Line 16: | ||
* [[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] | * [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] | ||
| − | * [http://openai.com/blog/emergent-tool-use/ Emergent Tool Use from Multi-Agent Interaction | + | * [http://openai.com/blog/emergent-tool-use/ Emergent Tool Use from Multi-Agent Interaction ...Hide and Seek 2019 |
Revision as of 14:17, 15 August 2020
Youtube search... ...Google search
- Case Studies
- 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
- [http://openai.com/blog/emergent-tool-use/ Emergent Tool Use from Multi-Agent Interaction ...Hide and Seek 2019
OpenAI Gym
OpenAI Gym and Universe
