List your company

Goal-conditioned navigation on MiniGrid 8x8 RGB image input (test)

0.43Clean RewardTDRT-PPO
0.36760.38380.40.4162Jun 6, 2024

Evaluation results

MethodLinks
TDRT-PPOTarget Reward=0.96 ± 02024.060.430.320.580.290.4
PPOTarget Reward=0.96 ± 0, Defense Status=No defense2024.060.370.50.920.480.63