Minimal Value-Equivalent Partial Models for Scalable and Robust Planning in Lifelong Reinforcement Learning

by   Safa Alver, et al.

Learning models of the environment from pure interaction is often considered an essential component of building lifelong reinforcement learning agents. However, the common practice in model-based reinforcement learning is to learn models that model every aspect of the agent's environment, regardless of whether they are important in coming up with optimal decisions or not. In this paper, we argue that such models are not particularly well-suited for performing scalable and robust planning in lifelong reinforcement learning scenarios and we propose new kinds of models that only model the relevant aspects of the environment, which we call "minimal value-equivalent partial models". After providing a formal definition for these models, we provide theoretical results demonstrating the scalability advantages of performing planning with such models and then perform experiments to empirically illustrate our theoretical results. Then, we provide some useful heuristics on how to learn these kinds of models with deep learning architectures and empirically demonstrate that models learned in such a way can allow for performing planning that is robust to distribution shifts and compounding model errors. Overall, both our theoretical and empirical results suggest that minimal value-equivalent partial models can provide significant benefits to performing scalable and robust planning in lifelong reinforcement learning scenarios.


page 5

page 16

page 17

page 19


Understanding Decision-Time vs. Background Planning in Model-Based Reinforcement Learning

In model-based reinforcement learning, an agent can leverage a learned m...

Discriminator Augmented Model-Based Reinforcement Learning

By planning through a learned dynamics model, model-based reinforcement ...

Visualizing MuZero Models

MuZero, a model-based reinforcement learning algorithm that uses a value...

Planning with Expectation Models

Distribution and sample models are two popular model choices in model-ba...

A Distributional Perspective on Reinforcement Learning

In this paper we argue for the fundamental importance of the value distr...

λ-AC: Learning latent decision-aware models for reinforcement learning in continuous state-spaces

The idea of decision-aware model learning, that models should be accurat...

Have I done enough planning or should I plan more?

People's decisions about how to allocate their limited computational res...

Please sign up or login with your details

Forgot password? Click here to reset