Continuous Control On Lunar Lander Openai Gym
평가 지표
Score
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Score | Paper Title | Repository |
|---|---|---|---|
| MAC | 163.5 | Mean Actor Critic | |
| TD3 | 277.26±4.17 | Addressing Function Approximation Error in Actor-Critic Methods | |
| DDPG | 256.98±14.38 | Continuous control with deep reinforcement learning | |
| PPO | 175.14±44.94 | Proximal Policy Optimization Algorithms | |
| SAC | 284.59±0.97 | Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor |
0 of 5 row(s) selected.