Pith. sign in

Researcher Evidence Record

Tadashi Kozuno

This bounded record lists 29 Pith paper rows and 0 imported work rows attributed to this corpus identity. The enumerated, non-disputed paper rows include cs.LG, stat.ML, cs.RO work dated 2017 to 2026. The record describes sources and coverage; it makes no judgment about the person.

Compiled coverage vector

Measured lane counts only. Not a trust score or person verdict.

Identity 2 canonical identity row plus typed public identifiers Pith papers 29 attributed paper rows in the Pith corpus, itemized below Imported works 0 imported works beyond the paper ledger Current reviews 5 of 29 papers carrying a current Pith review; presence, not outcome Sourced citations 8 of 29 works with a source-named citation count Coauthors 50 distinct coauthors across shared paper rows
Enumerated paper scope: 6 fields (cs.LG, stat.ML, cs.RO, +3 more) · 2017-2026 sources: authors, author_identifiers · paper_authors · author_works · current_verdicts · cited_works

A sourced case file for attributed work. It is neither a profile score nor a verdict about this researcher.

Attributed works

A bounded ledger from the Pith paper and imported-work queries. Counts and source confidence stay with each work.

  1. 2026 Pith paper

    Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying

    cs.LG provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  2. 2026 Pith paper

    The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback

    cs.LG provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Tadashi Kozuno
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  3. 2026 Pith paper

    Optimal last-iterate convergence in matrix games with bandit feedback using the log-barrier

    cs.LG provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Tadashi Kozuno
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  4. 2026 Pith paper

    Am I More Pointwise or Pairwise? Revealing Position Bias in Rubric-Based LLM-as-a-Judge

    cs.CL provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  5. 2025 Pith paper

    MK2 at PBIG Competition: A Prompt Generation Solution

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  6. 2024 Pith paper

    Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form

    cs.LG provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Tadashi Kozuno
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 2 pith inbound references from cited_work_pith_inbound_counts
  7. 2024 Pith paper

    Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability with a Soft Wrist

    cs.RO provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  8. 2024 Pith paper

    A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 2 pith inbound references from cited_work_pith_inbound_counts
  9. 2023 Pith paper

    Multi-Agent Behavior Retrieval: Retrieval-Augmented Policy Training for Cooperative Push Manipulation by Mobile Robots

    cs.RO provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  10. 2023 Pith paper

    Local and adaptive mirror descents in extensive-form games

    cs.GT provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  11. 2023 Pith paper

    DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  12. 2023 Pith paper

    Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  13. 2023 Pith paper

    Counterfactual Fairness Filter for Fair-Delay Multi-Robot Navigation

    cs.MA provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  14. 2023 Pith paper

    When to Replan? An Adaptive Replanning Strategy for Autonomous Navigation using Deep Reinforcement Learning

    cs.RO provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  15. 2023 Pith paper

    Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  16. 2023 Pith paper

    Robust Markov Decision Processes without Model Estimation

    stat.ML provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 2 pith inbound references from cited_work_pith_inbound_counts
  17. 2022 Pith paper

    Adapting to game trees in zero-sum imperfect information games

    stat.ML provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  18. 2022 Pith paper

    Confident Approximate Policy Iteration for Efficient Local Planning in $q^\pi$-realizable MDPs

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  19. 2022 Pith paper

    KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 2 pith inbound references from cited_work_pith_inbound_counts
  20. 2022 Pith paper

    No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    8
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  21. 2021 Pith paper

    Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  22. 2021 Pith paper

    Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  23. 2021 Pith paper

    Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall

    stat.ML provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  24. 2021 Pith paper

    Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  25. 2021 Pith paper

    Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  26. 2021 Pith paper

    Revisiting Peng's Q($\lambda$) for Modern Reinforcement Learning

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  27. 2020 Pith paper

    Leverage the Average: an Analysis of KL Regularization in RL

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  28. 2019 Pith paper

    Gap-Increasing Policy Evaluation for Efficient and Noise-Tolerant Reinforcement Learning

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  29. 2017 Pith paper

    Unifying Value Iteration, Advantage Learning, and Dynamic Policy Programming

    stat.ML provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Tadashi Kozuno
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.

Evidence apparatus

The machinery behind this record. Every lane states whether Pith measured it, did not query it, could not reach it, or withheld it.

LaneStateObservedBoundary and source
identity Measured 2 Canonical identity row plus public typed identifiers.
source=authors, author_identifiers
papers Measured 29 of 29 bounded rows Rows attributed to this author UUID in the Pith corpus.
source=paper_authors
works Measured zero 0 of 0 bounded rows Imported works not duplicated by the paper ledger.
source=author_works
reviews Measured 5 of 29 bounded rows Coverage count only. No review outcome is projected onto the person.
source=current_verdicts
citations Measured 8 of 29 bounded rows Counts remain itemized by work and source.
source=cited_works
coauthors Measured 50 of 29 bounded rows Shared-work edges from admitted paper rows.
source=paper_authors
account Unavailable No public count of 1 bounded rows Account metadata is separate from corpus evidence.
source=users.author_id
Public identity sources
  • name variant
    Tadashi Kozuno     backfill
    confidence 0.6

identity history

Enumerated research scope

Fields and dates come only from enumerated, non-disputed Pith paper rows. They do not claim career completeness.

  • cs.LG18 rows
  • stat.ML4 rows
  • cs.RO3 rows
  • cs.CL2 rows
  • cs.GT1 rows
  • cs.MA1 rows
  • 20171 rows
  • 20191 rows
  • 20201 rows
  • 20216 rows
  • 20224 rows
  • 20238 rows
  • 20243 rows
  • 20251 rows
  • 20264 rows
Shared-work index
Record scope

The work queries are bounded. Missing rows may mean measured zero, an unavailable source, a query that did not run, or private data that Pith withheld. The lane table keeps those cases separate.

Paper findings remain attached to papers. They do not become findings about this researcher.