Scalable Semantic Non-Markovian Simulation Proxy for Reinforcement Learning.
Kaustuv MukherjiDevendra ParkarLahari PokalaDyuman AdityaPaulo ShakarianClark DormanPublished in: ICSC (2024)
Keyphrases
- reinforcement learning
- reinforcement learning agents
- partially observable domains
- state space
- function approximation
- real robot
- machine learning
- simulation model
- optimal policy
- markov decision processes
- learning algorithm
- semantic network
- dynamic programming
- semantic information
- state abstraction
- semantic knowledge
- semantic search
- semantic similarity
- temporal difference
- simulation environment
- model free
- reinforcement learning algorithms
- situation calculus
- wordnet
- reinforcement learning methods
- dynamic environments
- multi agent