Comparing Deep Reinforcement Learning Algorithms' Ability to Safely Navigate Challenging Waters.
Thomas Nakken LarsenHalvor Ødegård TeigenTorkel LaacheDamiano VaragnoloAdil RasheedPublished in: Frontiers Robotics AI (2021)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- state space
- model free
- markov decision processes
- reinforcement learning problems
- reinforcement learning methods
- learning algorithm
- temporal difference
- eligibility traces
- policy search
- function approximation
- tabula rasa
- partially observable environments
- reward function
- dynamic environments
- function approximators
- search algorithm
- support vector
- decision making