Deterministic Policy Gradient Based Robotic Path Planning with Continuous Action Spaces.
Somdyuti PaulLovekesh VigPublished in: ICCV Workshops (2017)
Keyphrases
- action space
- path planning
- mobile robot
- state space
- markov decision processes
- state and action spaces
- real valued
- multiple robots
- aerial vehicles
- control policies
- reinforcement learning
- single agent
- action selection
- continuous state spaces
- path planning algorithm
- dynamic environments
- path finding
- continuous state
- obstacle avoidance
- collision avoidance
- markov decision process
- multi robot
- motion planning
- robot path planning
- stochastic processes
- robotic systems
- degrees of freedom
- markov decision problems
- optimal policy
- continuous action
- heuristic search
- autonomous robots
- optimal path
- dynamic and uncertain environments
- dynamic programming
- policy search
- unmanned aerial vehicles
- autonomous vehicles
- planning problems