Off-Policy Evaluation in Markov Decision Processes under Weak Distributional Overlap
Doubly robust methods hold considerable promise for off-policy evaluation in Markov decision processes (MDPs) under sequential ignorability: They have been shown to converge as $1/\sqrt{T}$ with the horizon $T$, to be statistically efficient in large samples, and to allow for modular implementation where preliminary estimation tasks can be executed using standard reinforcement learning techniques. Existing results, however, make heavy use of a strong distributional overlap assumption whereby the stationary distributions of the target policy and the data-collection policy are within a bounded factor of each other -- and this assumption is typically only credible when the state space of the MDP is bounded. In this paper, we re-visit the task of off-policy evaluation in MDPs under a weaker notion of distributional overlap, and introduce a class of truncated doubly robust (TDR) estimators which we find to perform well in this setting. When the distribution ratio of the target and data-collection policies is square-integrable (but not necessarily bounded), our approach recovers the large-sample behavior previously established under strong distributional overlap. When this ratio is not square-integrable, TDR is still consistent but with a slower-than-$1/\sqrt{T}$; furthermore, this rate of convergence is minimax over a class of MDPs defined only using mixing conditions. We validate our approach numerically and find that, in our experiments, appropriate truncation plays a major role in enabling accurate off-policy evaluation when strong distributional overlap does not hold.
Code (0)
등록된 구현이 없습니다.
Tasks
Off-policy evaluationSimilar Papers 제목 키워드 기반
Off-Policy Evaluation in Partially Observed Markov Decision Processes under Sequential Ignorability
We consider off-policy evaluation of dynamic treatment rules under sequential ignorability, given an assumption that the underlying system can be modeled as a partially observed Markov decision process (POMDP). We propos…
Off-policy evaluationReinforcement Learning with Function Approximation for Non-Markov Processes
We study reinforcement learning methods with linear function approximation under non-Markov state and cost processes. We first consider the policy evaluation method and show that the algorithm converges under suitable er…
Reinforcement LearningOff-Policy Evaluation for Episodic Partially Observable Markov Decision Processes under Non-Parametric Models
We study the problem of off-policy evaluation (OPE) for episodic Partially Observable Markov Decision Processes (POMDPs) with continuous states. Motivated by the recently proposed proximal causal inference framework, we …
Causal InferenceOff-policy evaluationA Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes
We consider off-policy evaluation (OPE) in Partially Observable Markov Decision Processes (POMDPs), where the evaluation policy depends only on observable variables and the behavior policy depends on unobservable latent …
Off-policy evaluationOff-Policy Evaluation in Partially Observable Environments
This work studies the problem of batch off-policy evaluation for Reinforcement Learning in partially observable environments. Off-policy evaluation under partial observability is inherently prone to bias, with risk of ar…
Off-policy evaluationReinforcement LearningReinforcement Learning (RL)