Pith. sign in

REVIEW 8 cited by

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 1912.02074 v1 pith:AVH7NMFA submitted 2019-12-04 cs.LG cs.AI

AlgaeDICE: Policy Gradient from Arbitrary Experience

classification cs.LG cs.AI
keywords objectivegradientmax-returnarbitrarydualexpectationformulationoff-policy
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In many real-world applications of reinforcement learning (RL), interactions with the environment are limited due to cost or feasibility. This presents a challenge to traditional RL algorithms since the max-return objective involves an expectation over on-policy samples. We introduce a new formulation of max-return optimization that allows the problem to be re-expressed by an expectation over an arbitrary behavior-agnostic and off-policy data distribution. We first derive this result by considering a regularized version of the dual max-return objective before extending our findings to unregularized objectives through the use of a Lagrangian formulation of the linear programming characterization of Q-values. We show that, if auxiliary dual variables of the objective are optimized, then the gradient of the off-policy objective is exactly the on-policy policy gradient, without any use of importance weighting. In addition to revealing the appealing theoretical properties of this approach, we also show that it delivers good practical performance.

discussion (0)

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

Forward citations

Cited by 8 Pith papers

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

  1. D4RL: Datasets for Deep Data-Driven Reinforcement Learning

    cs.LG 2020-04 accept novelty 8.0

    D4RL supplies new offline RL benchmarks and datasets from expert and mixed sources to expose weaknesses in existing algorithms and standardize evaluation.

  2. 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.

  3. 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.

  4. TRAM: Test-Time Risk Adaptation with Mixture of Agents

    cs.LG 2024-08 unverdicted novelty 7.0

    TRAM is a test-time mixture method that scores and composes risk-neutral source policies using reward and occupancy-based risk to achieve new reward-risk tradeoffs without parameter updates.

  5. VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training

    cs.RO 2022-09 unverdicted novelty 7.0

    VIP learns a visual embedding from human videos whose distance defines dense, smooth rewards for arbitrary goal-image robot tasks without task-specific fine-tuning.

  6. 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.

  7. Density-Ratio Weighted Behavioral Cloning: Learning Control Policies from Corrupted Datasets

    cs.LG 2025-10 conditional novelty 6.0

    Weighted BC estimates trajectory density ratios from a clean reference set via binary discrimination and reweights the BC loss to converge to the clean expert policy with finite-sample bounds independent of contaminat...

  8. Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems

    cs.LG 2020-05 unverdicted novelty 2.0

    Offline RL promises to extract high-utility policies from static datasets but faces fundamental challenges that current methods only partially address.