Reinforcement Learning on DeepMind Control Suite Easy & Medium benchmark leaderboard · SOTA2 Research

Reinforcement Learning on DeepMind Control Suite Easy & Medium

443.53Acrobot SwingupCIR

Evaluation Results

Method	Links
CIR2026.02		443.53	998.05	999.6	875.22	839.56	747	940.05	892.5	888.4	781.79	280.1	821.98	837.95	807	933.8	974.06	954.21	810.04	986.66	973.86	887.86	840.04	839.27	16.07
BRO2026.02		390.78	998.66	954.21	878.69	833.18	739.67	987.45	905.85	905.3	680.34	315.04	910.88	816.2	818.62	936.06	933.77	956.52	754.43	986.58	973.41	888.02	836.62	833.78	16.62
TD-MPC22026.02		361.07	993.93	1,000	876.07	844.77	757.6	984.63	854.67	876.27	610.23	303.27	936.47	841.7	939.63	957.17	919.43	913.73	820.4	957.17	978.7	895.47	836.93	836.34	16.37
DreamerV32026.02		360.46	994.95	800.25	863.9	262.69	686.25	434.06	851.11	769.86	603.34	192.7	722.42	825.17	471.25	472.31	888.36	935.25	620.13	963.28	925.46	748.58	684.18	682.16	31.78
SimBa2026.02		331.57	999.05	940.53	866.53	823.97	814.97	778.83	881.33	860.22	786.73	326.69	811.75	824.53	883.68	952.96	972.23	965.96	687.16	983.02	970.73	885.7	816.78	823.12	17.69
SAC2026.02		57.56	998.79	1,000	863.24	779.99	716.43	814.69	903.07	775.21	462.67	159.43	845.89	476.58	116.91	147.83	951.8	959.59	629.44	972.59	956.67	799.75	676.59	679.42	32.06
TD72026.02		39.83	998.79	988.58	878.09	480.74	897.76	592.74	485.66	596.32	108.84	110.27	445.5	461.4	515.13	910.55	920.38	549.5	782.32	984.63	976.58	740.19	623.18	636.18	36.38