A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation

by   Scott Fujimoto, et al.

Marginalized importance sampling (MIS), which measures the density ratio between the state-action occupancy of a target policy and that of a sampling distribution, is a promising approach for off-policy evaluation. However, current state-of-the-art MIS methods rely on complex optimization tricks and succeed mostly on simple toy problems. We bridge the gap between MIS and deep reinforcement learning by observing that the density ratio can be computed from the successor representation of the target policy. The successor representation can be trained through deep reinforcement learning methodology and decouples the reward optimization from the dynamics of the environment, making the resulting algorithm stable and applicable to high-dimensional domains. We evaluate the empirical performance of our approach on a variety of challenging Atari and MuJoCo environments.


page 7

page 8

page 21

page 22


Importance Sampling Policy Evaluation with an Estimated Behavior Policy

In reinforcement learning, off-policy evaluation is the task of using da...

Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning

Oftentimes, environments for sequential decision-making problems can be ...

Learning State Representations for Query Optimization with Deep Reinforcement Learning

Deep reinforcement learning is quickly changing the field of artificial ...

GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values

We present GradientDICE for estimating the density ratio between the sta...

Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization

Learning in a lifelong setting, where the dynamics continually evolve, i...

Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?

The use of deep reinforcement learning allows for high-dimensional state...

Wi-Fi Rate Adaptation using a Simple Deep Reinforcement Learning Approach

The increasing complexity of recent Wi-Fi amendments is making optimal R...

Please sign up or login with your details

Forgot password? Click here to reset