Latent-Conditioned Policy Gradient for Multi-Objective Deep Reinforcement Learning.
Takuya KanazawaChetan GuptaPublished in: CoRR (2023)
Keyphrases
- policy gradient
- multi objective
- reinforcement learning
- actor critic
- function approximation
- evolutionary algorithm
- reinforcement learning algorithms
- policy search
- optimization algorithm
- gradient method
- genetic algorithm
- objective function
- particle swarm optimization
- optimal control
- model free reinforcement learning
- latent variables
- temporal difference
- policy gradient methods
- reinforcement learning methods
- model free
- multi agent
- approximation methods
- variance reduction
- dynamic programming
- state space
- function approximators
- machine learning
- monte carlo
- average reward
- partially observable markov decision processes
- state action
- single agent
- control problems
- differential evolution
- control strategies