Reinforcement Learning using Reward Expectations in Scenarios with Aleatoric Uncertainties.
Yubin WangYifeng SunJiang WuHao HuZhiqiang WuWeigui HuangPublished in: CoG (2022)
Keyphrases
- reinforcement learning
- function approximation
- state space
- reinforcement learning algorithms
- eligibility traces
- model free
- machine learning
- multi agent
- optimal policy
- real world
- markov decision processes
- temporal difference
- transfer learning
- optimal control
- partially observable environments
- reward function
- monte carlo
- learning scenarios
- learning problems
- supervised learning
- mobile robot
- application scenarios
- learning process
- real robot
- learning agent
- temporal difference learning
- policy evaluation
- learning algorithm
- total reward
- data sets