Benchmarking Batch Deep Reinforcement Learning Algorithms.
Scott FujimotoEdoardo ContiMohammad GhavamzadehJoelle PineauPublished in: CoRR (2019)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- state space
- markov decision processes
- model free
- reinforcement learning problems
- reinforcement learning methods
- eligibility traces
- temporal difference
- learning algorithm
- function approximation
- stochastic games
- reward function
- partially observable environments
- policy search
- dynamic environments
- supervised learning
- active learning
- multiagent reinforcement learning
- multi agent
- evaluation function
- monte carlo
- linear programming
- prior knowledge
- search algorithm
- bayesian networks