A Distributional Perspective on Reinforcement Learning.
Marc G. BellemareWill DabneyRémi MunosPublished in: ICML (2017)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- markov decision processes
- optimal control
- genetic algorithm
- co occurrence
- state space
- real world
- reinforcement learning algorithms
- dynamic programming
- viewpoint
- information technology
- markov chain
- transfer learning
- image sequences
- learning problems
- database systems
- machine learning
- model free
- temporal difference
- neural network
- control problems
- learning agents
- multi agent reinforcement learning