Distributed Bayesian optimization of deep reinforcement learning algorithms.
M. Todd YoungJacob D. HinkleRamakrishnan KannanArvind RamanathanPublished in: J. Parallel Distributed Comput. (2020)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- model free
- markov decision processes
- state space
- learning algorithm
- reinforcement learning problems
- multi agent
- temporal difference
- function approximation
- bayesian networks
- eligibility traces
- reinforcement learning methods
- partially observable environments
- optimization algorithm
- machine learning
- maximum likelihood
- cooperative
- dynamic environments
- reward function
- dynamic programming
- tabula rasa
- optimal policy
- sufficient conditions