Policy Augmentation: An Exploration Strategy for Faster Convergence of Deep Reinforcement Learning Algorithms.
Arash MahyariPublished in: CoRR (2021)
Keyphrases
- faster convergence
- reinforcement learning algorithms
- exploration strategy
- reinforcement learning
- reinforcement learning problems
- markov decision problems
- optimal policy
- reward function
- step size
- state space
- model free
- function approximation
- markov decision processes
- temporal difference
- function approximators
- convergence speed
- markov decision process
- global optimum
- action selection
- partially observable
- pso algorithm
- policy iteration
- particle swarm optimization
- global optimization
- partially observable markov decision processes
- unknown environments
- linear programming
- machine learning
- neural network
- single agent
- cost function
- action space
- decision problems
- learning algorithm
- multiresolution
- multi agent