Reinforcement Learning (Atari Games) 벤치마크
Reinforcement Learning (Atari Games) on Seaquest - OpenAI Gym
| Rank | Model | Average Return | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | BanditDQN | 87 ± 45 | Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments | abhi460729/Action-Duration-with-Contextual-Bandits-for-Deep-Reinforcement-Learning-in-Dynamic-Environments | 2025 |