ResearchBenchmarksContinuous Control on Walker2d v3Follow4,013Average ReturnALH662.121,532.062,4023,271.94Jan 27, 2026Feb 8, 2026Feb 20, 2026Mar 4, 2026Mar 16, 2026Mar 28, 2026Apr 10, 2026Evaluation ResultsMethodMethodLinksAverage ReturnALH2026.014,013IRA2026.013,886PEER2026.013,605FedRL-PPO w/ PONPON=truePON=true2026.043,532.11TD32026.013,464FedRL-PPO2026.042,931DDPG2026.012,379PPO2026.042,304.43MBPO2026.011,389PPO2026.01791