Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model.
Thanh NguyenTung Minh LuuThang VuChang D. YooPublished in: IROS (2021)
Keyphrases
- reinforcement learning
- prior knowledge
- learning process
- learning algorithm
- probabilistic model
- hidden state
- mathematical model
- computational model
- machine learning
- probability distribution
- experimental data
- learning problems
- learning models
- learning mechanism
- connectionist networks
- dynamic programming
- high level
- highly nonlinear
- learning agents
- learning phase
- dynamic bayesian networks
- learning scheme
- learning tasks
- multi agent
- artificial neural networks
- supervised learning
- active learning