List your company

Continuous Control on Multimodal continuous control environment (final 80 episodes)

1,295.7Mean RewardQuantFPFlow
601.708781.879962.051,142.221May 14, 2026

Evaluation results

MethodLinks
QuantFPFlowtraining_episodes=400, averaging_window=final 80 episodes2026.051,295.72,235.533.95.877
SACtraining_episodes=400, averaging_window=final 80 episodes2026.051,2842,378.530.76.576
Randomtraining_episodes=400, averaging_window=final 80 episodes2026.05670.4355.20.13.319
DDPGtraining_episodes=400, averaging_window=final 80 episodes2026.05628.42,274.522.35.969