Continuous Control 벤치마크
Continuous Control on Simple Humanoid
Score
- 2016-04-22 — TRPO: Score 269.7
| Rank | Model | Score | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | TRPO | 269.7 | Benchmarking Deep Reinforcement Learning for Continuous Control | openai/rllab · rllab/rllab · rll/rllab · +12 | 2016 |
| 1 | TRPO | 269.7 | Benchmarking Deep Reinforcement Learning for Continuous Control | openai/rllab · rllab/rllab · rll/rllab · +12 | 2016 |
| 1 | TRPO | 269.7 | Benchmarking Deep Reinforcement Learning for Continuous Control | openai/rllab · rllab/rllab · rll/rllab · +12 | 2016 |