pith. sign in

Michael Dennis

Identifiers

  • name variant Michael Dennis 0.60 · backfill

Papers (23)

  1. Mitigating Goal Misgeneralization via Minimax Regret cs.LG · 2025 · author #7
  2. Multi-Agent Risks from Advanced AI cs.MA · 2025 · author #33
  3. BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping cs.LG · 2024 · author #2
  4. The Benefits of Power Regularization in Cooperative Reinforcement Learning cs.LG · 2024 · author #2
  5. Open-Endedness is Essential for Artificial Superhuman Intelligence cs.LG · 2024 · author #2
  6. Genie: Generative Interactive Environments cs.LG · 2024 · author #2
  7. Refining Minimax Regret for Unsupervised Environment Design cs.LG · 2024 · author #6
  8. minimax: Efficient Baselines for Autocurricula in JAX cs.LG · 2023 · author #2
  9. Stabilizing Unsupervised Environment Design with a Learned Adversary cs.LG · 2023 · author #4
  10. Who Needs to Know? Minimal Knowledge for Optimal Coordination cs.AI · 2023 · author #4
  11. MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning cs.LG · 2023 · author #3
  12. Cooperative and uncooperative institution designs: Surprises and problems in open-source game theory cs.GT · 2022 · author #2
  13. Grounding Aleatoric Uncertainty for Unsupervised Environment Design cs.LG · 2022 · author #2
  14. Sociotechnical Specification for the Broader Impacts of Autonomous Vehicles cs.CY · 2022 · author #3
  15. Evolving Curricula with Regret-Based Environment Design cs.LG · 2022 · author #3
  16. Replay-Guided Adversarial Environment Design cs.LG · 2021 · author #2
  17. A New Formalism, Method and Open Issues for Zero-Shot Coordination cs.AI · 2021 · author #2
  18. Improving Social Welfare While Preserving Autonomy via a Pareto Mediator cs.GT · 2021 · author #3
  19. Accumulating Risk Capital Through Investing in Cooperation cs.MA · 2021 · author #2
  20. Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design cs.LG · 2020 · author #1
  21. Quantifying Differences in Reward Functions cs.LG · 2020 · author #2
  22. Adversarial Policies: Attacking Deep Reinforcement Learning cs.LG · 2019 · author #2
  23. The Stretch Factor of Hexagon-Delaunay Triangulations cs.CG · 2017 · author #1

Mentions

  • 2507.03068 #7 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2409.05358 #2 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2502.14143 #33 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2311.12716 #2 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2406.11240 #2 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2402.12284 #6 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2406.04268 #2 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2402.15391 #2 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2203.01302 #3 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2308.10797 #4 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2306.09309 #4 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2106.06613 #2 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2303.03376 #3 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2207.05219 #2 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2208.07006 #2 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2205.07395 #3 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2110.02439 #2 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2106.03927 #3 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2101.10305 #2 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2006.13900 #2 · arxiv_oai · confidence 0.70 Michael Dennis
  • 2012.02096 #1 · arxiv_oai · confidence 0.70 Michael Dennis
  • 1905.10615 #2 · arxiv_oai · confidence 0.70 Michael Dennis
  • 1711.00068 #1 · arxiv_oai · confidence 0.70 Michael Dennis

Frequent Coauthors