GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms.
Cédric ColasOlivier SigaudPierre-Yves OudeyerPublished in: JFPDA (2018)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- state space
- model free
- markov decision processes
- gene expression programming
- reinforcement learning problems
- eligibility traces
- reinforcement learning methods
- temporal difference
- learning algorithm
- reward function
- function approximation
- markov chain
- partially observable environments
- action selection
- dynamic environments
- policy search
- hidden markov models
- genetic programming
- support vector machine
- neural network
- tabula rasa