Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search.
Ali YahyaAdrian LiMrinal KalakrishnanYevgen ChebotarSergey LevinePublished in: CoRR (2016)
Keyphrases
- policy search
- reinforcement learning
- continuous state
- modular robots
- robot navigation
- reinforcement learning algorithms
- mobile robot
- dynamic programming
- distributed systems
- multi agent
- robot control
- real robot
- vision system
- path planning
- partially observable markov decision processes
- continuous action
- multi robot
- markov decision processes
- action space
- function approximation
- model free
- temporal difference
- function approximators
- reinforcement learning methods
- policy gradient
- state space
- autonomous robots