Learning to Combat Compounding-Error in Model-Based Reinforcement Learning
Xiao, Chenjun, Wu, Yifan, Ma, Chen, Schuurmans, Dale, Müller, Martin
Despite its potential to improve sample complexity versus model-free approaches, model-based reinforcement learning can fail catastrophically if the model is inaccurate. An algorithm should ideally be able to trust an imperfect model over a reasonably long planning horizon, and only rely on model-free updates when the model errors get infeasibly large. In this paper, we investigate techniques for choosing the planning horizon on a state-dependent basis, where a state's planning horizon is determined by the maximum cumulative model error around that state. We demonstrate that these state-dependent model errors can be learned with Temporal Difference methods, based on a novel approach of temporally decomposing the cumulative model errors. Experimental results show that the proposed method can successfully adapt the planning horizon to account for state-dependent model accuracy, significantly improving the efficiency of policy learning compared to model-based and model-free baselines.
Dec-23-2019
- Country:
- North America
- Canada > Alberta (0.14)
- United States > Pennsylvania
- Allegheny County > Pittsburgh (0.04)
- Asia > Middle East
- Jordan (0.04)
- North America
- Genre:
- Research Report
- New Finding (0.34)
- Promising Solution (0.34)
- Research Report
- Technology: