Sven Mika b4790900f5 [RLlib] Sub-class Trainer (instead of build_trainer()): All remaining classes; soft-deprecate build_trainer. (#20725)		2021-12-04 22:05:26 +01:00
..
agents	[RLlib] Sub-class Trainer (instead of build_trainer()): All remaining classes; soft-deprecate build_trainer. (#20725)	2021-12-04 22:05:26 +01:00
envs	[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535)	2021-11-03 16:24:00 +01:00
examples	[RLlib] Unify all RLlib Trainer.train() -> results[info][learner][policy ID][learner_stats] and add structure tests. (#18879)	2021-09-30 16:39:05 +02:00
models	[RLlib] Fix bandit example scripts and add all scripts to CI testing suite.	2021-06-15 13:30:31 +02:00
__init__.py	Contextual Bandit algorithms (WIP) (#7642)	2020-03-26 13:41:16 -07:00
exploration.py	[RLlib] Fix bandit example scripts and add all scripts to CI testing suite.	2021-06-15 13:30:31 +02:00