| model-index: | |
| - name: PPO LunarLander-v2 | |
| results: | |
| - task: | |
| type: reinforcement-learning | |
| name: reinforcement-learning | |
| dataset: | |
| name: LunarLander-v2 | |
| type: LunarLander-v2 | |
| metrics: | |
| - type: mean_reward | |
| value: -132.23 +/- 107.40 | |
| name: mean_reward | |
| verified: false | |
| # PPO Agent for LunarLander-v2 | |
| Mean reward: -132.23 ± 107.40 |