Efficient Deep Reinforcement Learning with Predictive Processing Proximal Policy Optimization.
Burcu KüçükogluWalraaf BorkentBodo RueckauerNasir AhmadUmut GüçlüMarcel van GervenPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- optimal policy
- real time
- data processing
- action selection
- optimization problems
- optimization algorithm
- model free
- reinforcement learning problems
- policy search
- markov decision process
- state space
- information processing
- global optimization
- function approximation
- state and action spaces
- optimization process
- dynamic programming
- evolutionary algorithm
- multi agent
- machine learning
- neural network