Adaptive Symmetric Reward Noising for Reinforcement Learning.
Refael VivantiTalya D. Sohlberg-BarisShlomo CohenOrna CohenPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- learning capabilities
- adaptive control
- eligibility traces
- machine learning
- function approximation
- reinforcement learning algorithms
- learning algorithm
- partially observable environments
- markov decision processes
- model free
- learning problems
- reward function
- optimal policy
- policy iteration
- temporal difference learning
- actor critic
- dynamic programming
- robotic control
- optimal control
- reinforcement learning methods
- multi agent
- agent receives