Posterior Sampling for Deep Reinforcement Learning.
Remo SassoMichelangelo ConservaPaulo E. RauberPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- markov chain monte carlo
- random sampling
- state space
- reinforcement learning algorithms
- multi agent
- markov decision processes
- function approximation
- metropolis hastings
- sampling algorithm
- probability distribution
- optimal policy
- monte carlo
- posterior distribution
- posterior probability
- temporal difference
- bayesian framework
- probabilistic model
- dynamic programming
- learning algorithm
- data sets
- optimal control
- learning problems
- gaussian process
- supervised learning
- action selection
- policy iteration
- reinforcement learning methods
- transition model
- robotic control
- machine learning