List your company

Navigation on MiniWorld Sidewalk (final 200 train episodes)

44.3Episode LengthPPO + Stimuli
40.385666.807893.23119.6522May 12, 2026

Evaluation results

MethodLinks
PPO + StimuliReward Regime=Baseline2026.0544.321.810
PPO + VCReward Regime=Intrinsic Reward Only, theta_thr=0.952026.05100.2316.490
Base PPOReward Regime=Baseline2026.05116.8800
PPO + VCReward Regime=Composite Reward (Extrinsic + Intrinsic), theta_thr=0.252026.05126.385.710
PPO + VCReward Regime=Intrinsic Reward Only, theta_thr=0.252026.05130.592.090
PPO + VCReward Regime=Composite Reward (Extrinsic + Intrinsic), theta_thr=0.952026.05133.81.840
PPO + VCReward Regime=Intrinsic Reward Only, theta_thr=0.602026.05139.961.730
PPO + VCReward Regime=Composite Reward (Extrinsic + Intrinsic), theta_thr=0.602026.05142.161.430