Gradient Informed Proximal Policy Optimization
–Neural Information Processing Systems
We introduce a novel policy learning method that integrates analytical gradients from differentiable environments with the Proximal Policy Optimization (PPO) algorithm.
Neural Information Processing Systems
Feb-8-2026, 13:35:45 GMT
- Country:
- North America > United States > Maryland > Prince George's County > College Park (0.04)
- Genre:
- Research Report (0.46)
- Technology: