Implicit Kinematic Policies: Unifying Joint and Cartesian Action Spaces in End-to-End Robot Learning.
Aditya GanapathiPete FlorenceJake VarleyKaylee BurnsKen GoldbergAndy ZengPublished in: CoRR (2022)
Keyphrases
- end to end
- action space
- control policies
- state space
- markov decision processes
- optimal policy
- markov decision process
- reinforcement learning
- continuous state
- real valued
- state and action spaces
- markov decision problems
- skill learning
- admission control
- continuous action
- stochastic processes
- policy search
- congestion control
- reward function
- degrees of freedom
- action selection
- application layer
- markov chain
- cooperative
- scalable video
- single agent
- finite state
- path planning
- search space