Implementation of a variety of bandit algorithms, a paradigm in reinforcement learning.
d
scikit-bandit
public
2 stars
0 forks
0 issues
Commits
List of commits on branch master.Unverified
aa0a0a58304844f593682ff1fe7f0960977bd0d2LinUCB, both for the linear and the contextual linear bandits.
ddourouc05 committed 6 years ago
Unverified
f067c0e655620b17af913578c7698736d9e6bc07Slight increase in code coverage for adversarial bandits.
ddourouc05 committed 6 years ago
Unverified
0f21ed8bbe50f53b5f982c563044b136c32ed3eeOther way to force Covecov to ignore certain lines...
ddourouc05 committed 6 years ago
Unverified
43cfab65de8a382c57b0405ef08f5fdac43c69daForce coverage to ignore lines.
ddourouc05 committed 6 years ago
Unverified
d744290c366fc8591a34d0d01844a53fdb3106acAlso test may_stop_accepting_inputs and will_accept_input.
ddourouc05 committed 6 years ago
Unverified
7a6ffabccca3213e780e3c7faad1445a74602725Update README to include new badges.
ddourouc05 committed 6 years ago