List your company
ResearchFormerly WizWand

Reinforcement Learning on Seaquest Atari (classical)

4,759RewardH2RL++
-150.841,123.832,398.53,673.17Mar 6, 2026
Updated 7mo ago

Evaluation results

MethodLinks
H2RL++2026.034,759
PPO2026.033,247
H2RL2026.032,812
hPPO2026.031,906
H2RL+2026.031,802
hReason2026.031,186
BlendRL2026.03117
hDQN2026.03112
NUDGE2026.0363
Option-critic2026.0338