Learning to Run challenge: Synthesizing physiologically accurate motion using deep reinforcement learning.
Lukasz KidzinskiSharada P. MohantyCarmichael F. OngJennifer L. HicksSean F. CarrollSergey LevineMarcel SalathéScott L. DelpPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- supervised learning
- function approximation
- neural network
- knowledge acquisition
- unsupervised learning
- learning scheme
- learning capabilities
- relational reinforcement learning
- policy search
- autonomous learning
- temporal difference learning
- deep learning
- temporal difference
- learning problems
- learning tasks
- bayesian networks