Our new X account is live! Follow @wizwand_team for updates

Constrained Reinforcement Learning on PointReach

89.2Episodic Reward

CPO

Updated 4d ago

Evaluation Results

Method	Links
CPO 2025.12		89.2	33.3
e-COP 2025.12		81.5	24.5
P3O 2025.12		76.3	26.3
APPO 2025.12		74.3	26.3
PCPO 2025.12		73.2	24.9
FOCOPS 2025.12		65.1	24.8
IPO 2025.12		49.1	24.7
PPO-L 2025.12		46.1	25.1