coach/rl_coach/traces/Atari_NStepQ_pong/trace.csv

1	Episode #	Training Iter	In Heatup	ER #Transitions	ER #Episodes	Episode Length	Total steps	Epsilon	Shaped Training Reward	Training Reward	Update Target Network	Evaluation Reward	Shaped Evaluation Reward	Success Rate	Loss/Mean	Loss/Stdev	Loss/Max	Loss/Min	Learning Rate/Mean	Learning Rate/Stdev	Learning Rate/Max	Learning Rate/Min	Grads (unclipped)/Mean	Grads (unclipped)/Stdev	Grads (unclipped)/Max	Grads (unclipped)/Min	Discounted Return/Mean	Discounted Return/Stdev	Discounted Return/Max	Discounted Return/Min	Entropy/Mean	Entropy/Stdev	Entropy/Max	Entropy/Min	Q/Mean	Q/Stdev	Q/Max	Q/Min	Q Values/Mean	Q Values/Stdev	Q Values/Max	Q Values/Min	Value Loss/Mean	Value Loss/Stdev	Value Loss/Max	Value Loss/Min
2	1	0.0	1.0	1117.0	1.0	1117.0	1117.0	0.5			0.0																-1.5180229894995567	0.6998808293377133	-0.08930329112720292	-3.148474706421977
3	2	163.0	0.0	821.0	1.0	821.0	1938.0	0.4919541999999965	-21.0	-21.0	0.0																-2.405652578063971	0.6237147471281423	-0.7105532272722921	-3.3691179328950627									0.25339470000000003	0.06996354	0.40677336	-0.35897204	0.035283737	0.10252844	1.0475135	1.1831225500000001e-05
4	3	320.0	0.0	782.0	1.0	782.0	2720.0	0.4842905999999932	-21.0	-21.0	0.0																-2.4614277069600043	0.5586658402302739	-0.7105532272722921	-3.354852824180864									0.20715186	0.062277785999999995	0.35004243	0.0036477323	0.05950941	0.13284620000000003	0.55984885	1.9053832e-05
5	4	522.0	0.0	1009.0	1.0	1009.0	3729.0	0.4744023999999889	-19.0	-19.0	0.0																-1.74034851817599	0.8736518980911252	0.29537702481737355	-3.229858453919355									0.1964524	0.06919237	0.40447715	0.0016004617	0.08728501	0.21507107	0.96532106	3.7585607e-05
6	5	673.0	0.0	755.0	1.0	755.0	4484.0	0.4670033999999857	-21.0	-21.0	0.0																-2.5246431129611286	0.5835765895797549	-0.7105532272722921	-3.3699982440767453									0.16121916	0.030521521	0.26771998	0.09214279	0.11407282	0.2374467	0.7852985	0.00861873