Outcome-directed Reinforcement Learning by Uncertainty \& Temporal Distance-Aware Curriculum Goal Generation.
Daesol ChoSeungjae LeeH. Jin KimPublished in: ICLR (2023)
Keyphrases
- reinforcement learning
- temporal constraints
- spatio temporal
- function approximation
- temporal information
- temporal reasoning
- learning algorithm
- spatial and temporal
- generation process
- elementary school
- partial observability
- markov decision processes
- state space
- multi agent
- temporal patterns
- temporal difference
- temporal evolution