Novelty Search for Deep Reinforcement Learning Policy Network Weights by Action Sequence Edit Metric Distance.
Ethan C. JacksonMark DaleyPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- action selection
- optimal policy
- search algorithm
- distance measure
- distance function
- action space
- partially observable domains
- state action
- policy search
- distance metric
- hidden nodes
- markov decision process
- triangular inequality
- function approximation
- euclidean distance
- complex networks
- search space
- input patterns
- triangle inequality
- markov decision processes
- partially observable
- reinforcement learning algorithms
- policy iteration
- action sequences
- transition model
- reinforcement learning problems
- search result diversification
- similarity search
- number of distance computations