Spatio-temporal Value Semantics-based Abstraction for Dense Deep Reinforcement Learning.
Jihui NieDehui DuJiangnan ZhaoPublished in: CoRR (2024)
Keyphrases
- spatio temporal
- reinforcement learning
- state abstraction
- temporal abstractions
- spatial and temporal
- spatio temporal data
- reinforcement learning algorithms
- model free
- state space
- optimal policy
- markov decision processes
- multi agent
- function approximation
- learning algorithm
- spatial temporal
- image sequences
- space time
- moving objects
- data abstraction
- human actions
- temporal difference learning
- temporal difference
- spatio temporal patterns
- robotic control
- function approximators
- markov decision process
- action selection
- optimal control
- human motion
- learning problems
- high level