Reinforcement Learning on Atari 100k raw (test) benchmark leaderboard · SOTA2 Research

Reinforcement Learning on Atari 100k raw (test)

1,173.2AlienBBF

Evaluation Results

Method	Links
BBF2024.05		1,173.2	244.6	2,098.5	3,946.1	732.9	24,459.8	85.8	370.6	7,549.3	58,431.8	13,341.4	25.5	2,384.8	1,331.2	7,818.6	1,129.6	6,614.7	8,223.4	18,991.7	2,008.3	16.7	40.5	4,447.1	33,426.8	1,232.5	12,101.7	12	2.247	1.139
SR-SPR2024.05		1,107.8	203.4	1,088.9	903.1	531.7	17,671	45.8	25.5	2,362.1	45,544.1	2,814.4	25.4	2,584.8	712.4	8,524	389.1	3,631.7	5,911.8	18,649.4	1,574.1	2.9	97.9	4,044.1	13,463.4	819	112,450.3	9	1.271	0.7
SPR2024.05		841.9	179.7	565.6	962.5	345.4	14,834.1	35.7	19.6	946.3	36,700.5	517.6	19.3	1,170.7	660.6	5,858.6	366.5	3,617.4	3,681.6	14,783.2	1,318.4	-5.4	86	866.3	12,213.1	558.1	10,859.2	6	0.616	0.337
EfficientZero2024.05		808.5	148.6	1,263.1	25,557.8	351	13,871.2	52.7	414.1	1,117.3	83,940.2	13,003.9	21.8	296.3	3,260.3	9,315.9	517	724.1	5,663.3	30,944.8	1,281.2	20.1	96.7	13,781.9	17,751.3	1,100.2	17,264.2	14	1.943	1.047
DIAMOND2024.05		744.1	225.8	1,526.4	3,698.5	19.7	4,702	86.9	132.5	1,369.8	99,167.8	288.1	33.3	274.1	5,897.9	5,621.8	427.4	5,382.2	8,610.1	18,713.6	1,958.2	20.4	114.3	4,499.3	20,673.2	551.2	3,856.3	11	1.459	0.641
CURL2024.05		711	113.7	500.9	567.2	65.3	8,997.8	0.9	2.6	783.5	9,154.4	646.5	28.3	1,226.5	400.9	4,987.7	331	740.2	3,049.2	8,155.6	1,064	-18.5	81.9	727	5,006.1	315.2	2,646.4	2	0.261	0.113
MuZero2024.05		530	38.8	500.1	1,734	192.5	7,687.5	15.1	48	1,350	56,937	3,527	21.8	255	1,256	3,095	87.5	62.5	4,890.8	18,813	1,265.6	-6.7	56.3	3,952	2,500	208	2,896.9	5	0.562	0.288