Minimal Value-Equivalent Partial Models for Scalable and Robust Planning in Lifelong Reinforcement Learning.
Safa AlverDoina PrecupPublished in: CoLLAs (2023)
Keyphrases
- reinforcement learning
- machine learning
- ai planning
- complex systems
- probabilistic model
- learning process
- multi agent
- image sequences
- artificial neural networks
- decision trees
- hidden markov models
- e learning
- state space
- computationally efficient
- optimal policy
- decision making
- heuristic search
- experimental data
- statistical models
- computational models
- data sets