Reward Conditioned Neural Movement Primitives for Population Based Variational Policy Optimization.
M. Tuluhan AkbulutUtku BozdoganAhmet E. TekdenEmre UgurPublished in: CoRR (2020)
Keyphrases
- combinatorial optimization
- global optimization
- image segmentation
- optimization process
- optimal policy
- partially observable environments
- network architecture
- optimization problems
- neural network
- inverse reinforcement learning
- high level
- optimization method
- reinforcement learning
- low level
- simulated annealing
- optimization algorithm
- particle swarm optimization
- markov chain
- artificial neural networks
- multiscale
- image sequences
- image processing