Eric Liang 2d543b6e19 [rllib] Refactor DQN to use an Evaluator abstraction (#1276) ... This introduces rllib.Evaluator and rllib.Optimizer classes. Optimizers encapsulate a particular distributed optimization strategy for RL. Evaluators encapsulate the model graph, and once implemented, any Optimizer may be "plugged in" to any algorithm that implements the Evaluator interface.		2017-12-06 17:51:57 -08:00
..
multi_node_tests	Fix actor garbage collection by breaking cyclic references (#1064)	2017-10-05 00:55:33 -07:00
multi_node_docker_test.py	Fixing Lint after flake upgrade (#1162)	2017-10-26 21:02:07 -05:00
run_multi_node_tests.sh	[rllib] Refactor DQN to use an Evaluator abstraction (#1276)	2017-12-06 17:51:57 -08:00