OpenAI Gym
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Continuous Control | OpenAI Gym Reacher (held-out λc ∈ {2, 3, 4}) | Reward-6.093 | 8 | |
| 2D bipedal locomotion | Hardcore (OpenAI Gym) (test) | Average Return140.1 | 6 | |
| 2D bipedal locomotion | Basic (OpenAI Gym) (test) | Average Return312 | 6 | |
| Reinforcement Learning | OpenAI Gym Humanoid v1 | Mean Reward6,849 | 3 | |
| Reinforcement Learning | OpenAI Gym Ant v1 | Mean Reward5,007 | 3 | |
| Reinforcement Learning | OpenAI Gym Walker v1 | Mean Reward5,867 | 3 | |
| Reinforcement Learning | OpenAI Gym Cheetah v1 | Mean Reward6,620 | 3 | |
| Reinforcement Learning | OpenAI Gym Hopper v1 | Mean Reward3,810 | 3 | |
| Reinforcement Learning | OpenAI Gym Swimmer v1 | Mean Reward366 | 3 | |
| Reinforcement Learning | OpenAI Gym Humanoid | Episodes96,720 | 3 | |
| Reinforcement Learning | OpenAI Gym Ant | Number of Episodes73,500 | 3 | |
| Reinforcement Learning | OpenAI Gym Walker | Episode Count14,250 | 3 | |
| Reinforcement Learning | OpenAI Gym Cheetah | Number of Episodes11,250 | 3 | |
| Reinforcement Learning | OpenAI Gym Hopper | Episode Count13,920 | 3 | |
| Reinforcement Learning | OpenAI Gym Swimmer | Number of Episodes1,550 | 2 | |
| Control Task | OpenAI Gym LunarLander | T-statistic-1.8707 | 1 | |
| Control Task | OpenAI Gym MountainCar | T-statistic-6.2431 | 1 | |
| Control Task | OpenAI Gym CarRacing | T-statistic-6.3987 | 1 | |
| Control Task | OpenAI Gym BipedalWalker | T-statistic-2.0642 | 1 | |
| Reinforcement Learning | OpenAI Gym Walker | Metric- | 0 | |
| Reinforcement Learning | OpenAI Gym Hopper | Metric- | 0 | |
| Reinforcement Learning | OpenAI Gym HalfCheetah | Metric- | 0 |
Showing 22 of 22 rows