52 commits

Author	SHA1	Message	Date
Matthew A. Wright	3131e1742d	[rllib] Qmix off by 1 in double Q calculation (#5731) ... * Qmix fix. -Current version of double Q learning is incorrect; it selects actions at timestep t instead of t+1 when computing the t+1 Q value. * Allow extra obs dict keys * Move Q-value-computing replay code to own function * Run the autoformatter * use better terms in comments ("policy" network instead of "live" network)	2019-09-18 18:12:30 -07:00
Eric Liang	5d7afe8092	[rllib] Try moving RLlib to top level dir (#5324)	2019-08-05 23:25:49 -07:00