Reinforcement Learning Generalization on Procgen 16 games (train) benchmark leaderboard · SOTA2 Research

Reinforcement Learning Generalization on Procgen 16 games (train)

27.5bigfishEDE

Evaluation Results

Method	Links
EDE2023.06		27.5	46.9	27.7	10.6	9.1	8.2	10.6	6.6	9	2.2	10	15.9	7.2	9	5.7	1.1
EDE2023.06		27.5	46.9	27.7	10.6	9.1	8.2	10.6	6.6	9	2.2	10	15.9	7.2	9	5.7	1.1
IDAAC2023.06		21.8	38.6	29.1	10.4	8.9	24.6	6.2	9.8	8.7	7.5	10.2	4.9	4.5	8.3	6.4	11.5
IDAAC2023.06		21.8	38.6	29.1	10.4	8.9	24.6	6.2	9.8	8.7	9	7.5	10.2	4.9	4.5	8.3	6.4
DAAC2023.06		20.1	38	29.7	10	8.8	22.5	5.8	9.8	8.7	6.9	10	5.2	5.2	8	6.6	11.3
DAAC2023.06		20.1	38	29.7	10	8.8	22.5	5.8	9.8	6.9	10	10.2	5.2	5.2	8	6.6	11.3
PPG2023.06		19.9	49.6	31.1	11.1	8.9	16.4	9.5	9.9	8.7	10.7	10.2	5.5	7.4	9.3	9	11.3
PPG2023.06		19.9	49.6	31.1	11.1	8.9	16.4	9.5	9.9	8.7	10.7	10.2	5.5	7.4	9.3	9	11.3
MixReg2023.06		15	28.7	29.9	7.9	8.2	6.2	6.2	9.5	8.5	3.6	7.5	9.1	4.4	3.2	8.7	8.9
MixReg2023.06		15	28.7	29.9	7.9	8.2	6.2	6.2	9.5	8.5	3.4	7.5	5.1	3.2	5.5	8.7	8.9
UCB-DRAC2023.06		12.8	33.1	29.3	8.1	8	10.2	5.8	9.4	8.2	7	8.6	7.3	6.2	5	8.5	12
UCB-DRAC2023.06		12.8	33.1	29.3	8.1	8	10.2	5.8	9.4	8.2	7	8.6	7.3	7.3	5	8.5	12
PPO2023.06		9.2	29	28.8	8	7.3	6.1	6.7	9.4	8.3	4.1	6.9	5.3	7.1	5.5	9.1	11.7
PPO2023.06		9.2	29	28.8	8	7.3	6.1	6.7	9.4	8.3	4.1	6.9	5.3	7.1	5.5	9.1	11.7
PLR2023.06		7.8	2.6	15.9	8.7	5.4	4.1	6.4	5.4	8.5	3.6	6.3	2	1.2	6.4	4.1	9.7
PLR2023.06		7.8	2.6	15.9	8.7	5.4	4.1	6.4	5.4	6.3	6.2	4.4	2	1.2	6.4	4.1	9.7