ResearchBenchmarksTrotting Gait Control on Unitree Go2 Simulated (test)Follow15.817Average Episode Reward (ρ=0)PPO-PGDLC12.4692413.3383714.207515.07663Apr 22, 2024Evaluation ResultsMethodMethodLinksAverage Episode Reward (ρ=0)Average Episode Reward (ρ=1)Average Episode Reward (ρ=2)Average Episode Reward (ρ=3)PPO-PGDLCλ=5 × 10−5, ϵ=0.001λ=5 × 10−5, ϵ=0.0012024.0415.81715.6214.35211.153PPO-PGDLCλ=10−2, ϵ=0.001λ=10−2, ϵ=0.0012024.0415.6615.04513.67111.74PPO-PGDLCλ=10−4, ϵ=0.001λ=10−4, ϵ=0.0012024.0415.21814.63713.4211.961PPO2024.0415.20714.83913.95812.377PPO-PGDLCλ=10−3, ϵ=0.001λ=10−3, ϵ=0.0012024.0412.59812.1811.67110.782