A Distributional Perspective on Reinforcement Learning.
Marc G. BellemareWill DabneyRémi MunosPublished in: CoRR (2017)
Keyphrases
- reinforcement learning
- function approximation
- co occurrence
- multi agent
- temporal difference
- viewpoint
- reinforcement learning algorithms
- markov decision processes
- databases
- model free
- optimal policy
- multi agent reinforcement learning
- multiple perspectives
- robot control
- sufficient conditions
- supervised learning
- state space
- hidden markov models
- expert systems
- artificial intelligence
- learning algorithm