A Review of Self-balancing Robot Reinforcement Learning Algorithms.
Aistis RaudysAusra SubonienePublished in: ICIST (2020)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- markov decision processes
- state space
- model free
- reinforcement learning problems
- learning algorithm
- mobile robot
- eligibility traces
- temporal difference
- function approximation
- robot navigation
- reinforcement learning methods
- policy search
- multi robot
- dynamic environments
- reward function
- learning agent
- partially observable environments
- monte carlo
- markov chain
- decision making
- step size
- multi agent
- reward shaping