Kagaratsch
Reputation: 1023
Proximal Policy Optimization Algorithms paper - definition of "KL" operation?
In the original paper on Proximal Policy Optimization Algorithms
in equation (4) the authors use an operation denoted by KL[]. Unfortunately, they never give a definition for it.
My question:
What does the
KL[]operation stand for?
Upvotes: 1
Views: 83
Answers (1)
Mark Ma
Reputation: 1362
Maybe it's KL divergence?
KL divergence is used to compare differences between two probability distribution.
Upvotes: 3
Related Questions
- What is the way to understand Proximal Policy Optimization Algorithm in RL?
- Why is RL called 'reinforcement' learning?
- Objective function in proximal policy optimization
- What is the meaning of the implementation of the KL divergence in Keras?
- Can state in Proximal Policy Optimization contain history?
- How to implement Proximal Policy Optimization (PPO) Algorithm for classical control problems?
- TRPO/PPO importance sampling term in loss function
- Why does Q-learning work in an unknown environment?
- Reward function for Policy Gradient Descent in Reinforcement Learning
- How do I describe optimal policy (pi*) of bellman's equation?