PPO_Lagrangian_PyTorch icon indicating copy to clipboard operation
PPO_Lagrangian_PyTorch copied to clipboard

verified publisher icon akjayant
→

Metadata

Implementation of PPO Lagrangian in PyTorch

trafficstars

PPO Lagrangian Reproduction in Pytorch

Implementation of PPO Lagrangian from Benchmarking Safe Exploration in Deep Reinforcement Learning Paper (Ray et al, 2019) in PyTorch

python ppo.py

Results

  1. Reward Returns
    reward
  2. Cost Returns (Cost limit=25)
    cost

← Metadata

34
Stars
10
Forks
Watchers

Owner

verified publisher icon akjayant

Metadata

Implementation of PPO Lagrangian in PyTorch

Back