Mesh-based Tools to Analyze Deep Reinforcement Learning Policies for Underactuated Biped Locomotion.
Nihar TaleleKatie BylPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- optimal policy
- degrees of freedom
- policy search
- robot control
- state space
- function approximation
- software tools
- markov decision process
- markov decision processes
- multi agent
- mechanical systems
- control parameters
- reinforcement learning algorithms
- multi modal
- mobile robot
- dynamic programming
- fitted q iteration