| tags: | |
| - LunarLander-v2 | |
| - ppo | |
| - deep-reinforcement-learning | |
| - reinforcement-learning | |
| - custom-implementation | |
| - deep-rl-course | |
| model-index: | |
| - name: PPO | |
| results: | |
| - task: | |
| type: reinforcement-learning | |
| name: reinforcement-learning | |
| dataset: | |
| name: LunarLander-v2 | |
| type: LunarLander-v2 | |
| metrics: | |
| - type: mean_reward | |
| value: 36.61 +/- 48.08 | |
| name: mean_reward | |
| verified: false | |
| # PPO Agent Playing LunarLander-v2 | |
| 평균 보상: 36.61 +/- 48.08 | |