Viewing profile — RuiWang0811

there are loads of env businesses for coding tasks, enterprise tasks, computer use etc etc. we offer different envs from a niche industry, which just so happens to be a very hard d…

We have experiments showing that agents at least can learn from the environment by overfitting on train. But we do not yet have full post train runs, mainly due to time. But follow…

We use real historical market data for the environments. There is no parametric modelling involved. The decay property refers to alpha that we give the agent for trade in the env -…

No we sell our own research to AI labs as RL envs. Realistic RL envs grows in demand as labs seek better data train better models. It’s a complimentary business. Simply put: we sel…

languagelearner, I think you need to spend more time learning languages

this seems to be a common misconception, our envs use market data, but the goal is not (only) trading. Market data just happens to be a good source of hard data science tasks. Re t…

we do affine transformations of the data, so all return/ pnl measures are still the same as with untransformed data. The transformation doesn’t change the conditional distribution …

not sure about your background, the trace shows the feature engineering the LLMs did

cofounder here - LLMs can do some model training, they train on ML competition data after all. But they do struggle with low signal to noise ratio of market data. But that’s exactl…

Does this mean you have to retrain routing rules every time a new model gets released? I imagine since the price/token (or rather the amount of work that can be done per token) doe…

With all the benchmaxxing happening, current evals are oversaturating and become meaningless for model comparison. I think there is only one test that can't be gamed: let them trad…

[dead]