Pith. sign in

REVIEW 5 cited by

A Variant of the Wang-Foster-Kakade Lower Bound for the Discounted Setting

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2011.01075 v2 pith:O5XEB4P7 submitted 2020-11-02 cs.LG cs.AIstat.ML

A Variant of the Wang-Foster-Kakade Lower Bound for the Discounted Setting

classification cs.LG cs.AIstat.ML
keywords discountedlearningsettingadaptedamountbatchboundcase
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Recently, Wang et al. (2020) showed a highly intriguing hardness result for batch reinforcement learning (RL) with linearly realizable value function and good feature coverage in the finite-horizon case. In this note we show that once adapted to the discounted setting, the construction can be simplified to a 2-state MDP with 1-dimensional features, such that learning is impossible even with an infinite amount of data.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Fitted Occupancy-Ratio Evaluation without Bellman Completeness

    stat.ML 2026-07 accept novelty 7.0

    FORE estimates discounted occupancy ratios by iterating KL-projected adjoint Bellman updates, achieving convergence under ratio realizability alone without Bellman completeness.

  2. Fitted $Q$ Evaluation Without Bellman Completeness via Stationary Weighting

    stat.ML 2025-12 conditional novelty 7.0

    Stationary-weighted FQE achieves finite-sample linear convergence to the projected Bellman fixed point without Bellman completeness by reweighting regressions to the target stationary norm.

  3. Bellman Calibration for $V$-Learning in Offline Reinforcement Learning

    stat.ML 2025-12 unverdicted novelty 7.0

    Bellman calibration supplies a new reliability criterion and post-hoc recalibration method for value functions in offline RL, with finite-sample guarantees at one-dimensional nonparametric rates that avoid Bellman com...

  4. Inverse Reinforcement Learning with Just Classification and a Few Regressions

    cs.LG 2025-09 unverdicted novelty 7.0

    GenPQR recovers normalized rewards in maximum-entropy IRL by estimating the policy with classification and the soft Q-function with regression, providing modular finite-sample guarantees under general function approximation.

  5. Stationary Reweighting Yields Local Convergence of Soft Fitted Q-Iteration

    stat.ML 2025-12 unverdicted novelty 6.0

    Stationary reweighting of soft fitted Q-iteration yields finite-sample local linear convergence to the projected fixed point under approximate realizability and controlled weighting error, even without Bellman completeness.