Scalable Semantic Non-Markovian Simulation Proxy for Reinforcement Learning.
Kaustuv MukherjiDevendra ParkarLahari PokalaDyuman AdityaPaulo ShakarianClark DormanPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- real robot
- state space
- model free
- robocup soccer
- semantic network
- markov decision processes
- partially observable domains
- optimal policy
- simulation model
- learning algorithm
- markov decision process
- semantic search
- learning process
- multi agent
- decision problems
- semantic annotation
- semantic similarity
- domain independent
- load balancing
- mathematical model
- visual features
- temporal difference
- reward function
- reinforcement learning algorithms
- natural language
- web services
- machine learning