Research Engineer@CHAI
///
Writer of code, explainer of ideas, wrangler of cats
-
Center for Human-Compatible AI
- United States
- http://decodyng.com
Pinned Loading
-
mvp_ray_sacred
mvp_ray_sacred PublicSimple example showing how to integrate Ray parallelization with the Sacred experiment framework
-
subspace_clustering
subspace_clustering PublicCode from a project to find newly-dense regions of categorical feature space using the technique here: https://www.cs.cornell.edu/johannes/papers/1998/sigmod1998-clique.pdf
Python 2
-
HumanCompatibleAI/adversarial-policies
HumanCompatibleAI/adversarial-policies PublicFind best-response to a fixed policy in multi-agent RL
-
HumanCompatibleAI/learning-from-human-preferences
HumanCompatibleAI/learning-from-human-preferences PublicReproduction of OpenAI and DeepMind's "Deep Reinforcement Learning from Human Preferences"
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.