Conservative Exploration in Reinforcement Learning.
Evrard GarcelonMohammad GhavamzadehAlessandro LazaricMatteo PirottaPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- active exploration
- exploration strategy
- action selection
- exploration exploitation
- autonomous learning
- model based reinforcement learning
- function approximation
- active learning
- state space
- stochastic approximation
- model free
- markov decision processes
- policy search
- learning algorithm
- temporal difference
- markov decision problems
- bandit problems
- balancing exploration and exploitation
- interactive exploration
- real world
- exploration exploitation tradeoff
- temporal difference learning
- temporal abstractions
- partially observable
- learning problems
- monte carlo
- evolutionary algorithm
- learning process
- multi agent
- case study
- decision trees
- machine learning