Reward Reports for Reinforcement Learning.
Thomas Krendl GilbertNathan LambertSarah DeanTom ZickAaron J. SnoswellSoham MehtaPublished in: AIES (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model free
- eligibility traces
- machine learning
- learning algorithm
- multi agent
- reinforcement learning algorithms
- markov decision processes
- temporal difference
- reward function
- dynamic programming
- optimal policy
- temporal difference learning
- data mining
- agent learns
- optimal control
- transfer learning
- supervised learning
- planning problems
- learning problems
- average reward
- state action
- learning agents
- reinforcement learning methods
- policy gradient
- learning process
- robotic control
- partially observable environments