On Inductive Biases in Deep Reinforcement Learning.
Matteo HesselHado van HasseltJoseph ModayilDavid SilverPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- machine learning
- function approximation
- inductive learning
- reinforcement learning algorithms
- state space
- concept learning
- inductive bias
- temporal difference
- multi agent
- inductive logic programming
- markov decision processes
- robotic control
- multi agent reinforcement learning
- model free
- optimal control
- dynamic programming
- decision making
- neural network
- learning algorithm
- control problems
- data sets
- deductive reasoning
- relational reinforcement learning
- policy search
- temporal difference learning
- learning agents
- deep learning
- learning problems
- artificial intelligence
- information systems
- objective function
- knowledge representation
- optimal policy
- transfer learning