Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration.
Desik RengarajanGargi VaidyaAkshay SarveshDileep M. KalathilSrinivas ShakkottaiPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- state space
- machine learning
- sparse data
- reward function
- model free
- multi agent
- optimal control
- learning problems
- high dimensional
- optimal policy
- total reward
- sparse matrix
- temporal difference
- real time
- learning algorithm
- reinforcement learning algorithms
- partially observable
- robotic control
- reward shaping
- reinforcement learning methods
- temporal difference learning
- action selection
- hidden markov models
- learning classifier systems
- dynamic programming
- supervised learning