Reinforcement Learning on Swimmer v4
128.5Average Episodic RewardFedNPG-ADMM
Evaluation results
| Method | Links | |
|---|---|---|
| FedNPG-ADMMNumber of Agents=82026.05 | 128.5 | |
| FedNPG-ADMMNumber of Agents=42026.05 | 127.2 | |
| FedNPGNumber of Agents=82026.05 | 124.8 | |
| FedNPG-ADMMNumber of Agents=22026.05 | 123.6 | |
| FedNPGNumber of Agents=42026.05 | 122.1 | |
| FedNPGNumber of Agents=22026.05 | 119.5 | |
| FedNPGNumber of Agents=12026.05 | 111.9 | |
| PDAEnvironment steps=1M, Number of seeds=10, Tests per epoch=102026.03 | 111.3 | |
| FedNPG-ADMMNumber of Agents=12026.05 | 109.4 | |
| PPOEnvironment steps=1M, Number of seeds=10, Tests per epoch=102026.03 | 54.2 | |
| TRPOEnvironment steps=1M, Number of seeds=10, Tests per epoch=102026.03 | 35 | |
| NPGEnvironment steps=1M, Number of seeds=10, Tests per epoch=102026.03 | 25.1 |