Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Bellman-consistent Pessimism for Offline Reinforcement Learning
Authors: Tengyang Xie, Ching-An Cheng, Nan Jiang, Paul Mineiro, Alekh Agarwal
NeurIPS 2021 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Our theoretical guarantees only require Bellman closedness as standard in the exploratory setting, in which case bonus-based pessimism fails to provide guarantees. The approach uses the offline dataset to first compute a lower bound on the value of each policy ฯ ฮ , and then returns the policy with the highest pessimistic value estimate. While this high-level template is at the heart of many recent approaches [e.g., Fujimoto et al., 2019; Kumar et al., 2019; Liu et al., 2020; Kidambi et al., 2020; Yu et al., 2020; Kumar et al., 2020], our main novelty is in the design and analysis of Bellman-consistent pessimism for general function approximation. As of limitations and future work, the sample complexity of our practical algorithm is worse than that of the information-theoretic approach, and it will be interesting to close this gap. Another future direction is to empirically evaluate PSPI on benchmarks and compare it to existing approaches. |
| Researcher Affiliation | Collaboration | Tengyang Xie UIUC EMAIL Ching-An Cheng Microsoft Research EMAIL Nan Jiang UIUC EMAIL Paul Mineiro Microsoft Research EMAIL Alekh Agarwal Google Research EMAIL |
| Pseudocode | Yes | Algorithm 1 PSPI: Pessimistic Soft Policy Iteration |
| Open Source Code | No | The paper does not provide any links to open-source code for the described methodology, nor does it state that such code will be released or is available in supplementary materials. |
| Open Datasets | No | We assume the standard i.i.d. data generation protocol in our theoretical derivations, that the offline dataset D consists of n i.i.d. (s, a, r, s ) tuples generated as (s, a) ยต, r = R(s, a), s P( |s, a) for some data distribution ยต. The paper discusses 'a pre-collected dataset' but does not name a specific public dataset or provide access details for any dataset used. |
| Dataset Splits | No | The paper is theoretical and does not describe empirical experiments or dataset usage with specific train/validation/test splits. |
| Hardware Specification | No | The paper is theoretical and does not report on empirical experiments, thus no hardware specifications for running experiments are provided. |
| Software Dependencies | No | The paper is theoretical and does not report on empirical experiments; therefore, no specific software dependencies with version numbers are mentioned. |
| Experiment Setup | No | The paper is theoretical and does not describe an experimental setup with specific hyperparameters or system-level training settings. |