Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics.
Krishan RanaMing XuBrendan TiddMichael MilfordNiko SünderhaufPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- motor skills
- action space
- learning algorithm
- state space
- learning problems
- action selection
- reinforcement learning methods
- supervised learning
- control policies
- state action
- policy search
- continuous state spaces
- continuous state
- function approximators
- markov decision process
- control problems
- markov decision processes
- path planning
- graphical models
- dynamic programming