Go to the Indico Home Page Up to category
  • Compact style
  • Indico style
  • Indico style - inline minutes
  • Indico style - numbered
  • Indico style - numbered + minutes
  • Indico Weeks View
    • Switch to the management area of this event
    Login

    3rd International Reinforcement Learning Bootcamp 2026

    16–18 Sept 2026
    PLUS University Salzburg
    Europe/Vienna timezone

    Contact

    Contribution List

    14 out of 14 displayed
    Export to PDF
    1. 1. Opening & Orientation (OPEN)
      Simon Hirlaender (Paris Lodron Universität Salzburg (PLUS) / IDA Lab)
      16/09/2026, 13:00

      Scope of Bootcamp 2026, schedule, logistics, and onboarding.

      Go to contribution page
    2. 2. Lecture 1: Introduction to Reinforcement Learning: "No Math, No Panic" (LEC-01)
      Olga Mironova (Paris Lodron Universität Salzburg (PLUS) / IDA Lab), Simon Hirlaender (Paris Lodron Universität Salzburg (PLUS) / IDA Lab)
      16/09/2026, 13:15
      Lectures

      RL mindset, agent-environment loop, return G_t, discount factor gamma, and exploration vs exploitation.

      Go to contribution page
    3. 3. Lecture 2: Reinforcement Learning Fundamentals: "From Words to Equations" (LEC-02)
      Simon Hirlaender (Paris Lodron Universität Salzburg (PLUS) / IDA Lab)
      16/09/2026, 14:00
      Lectures

      Markov Decision Processes, Bellman expectation and optimality equations, value decomposition (V, Q, A), and tabular updates.

      Go to contribution page
    4. 4. Tutorial 1: Tabular RL & Discrete MDPs (TUT-01)
      Leander Grech (Paris Lodron Universität Salzburg (PLUS)), Léa Keller (Paris Lodron Universität Salzburg (PLUS))
      16/09/2026, 15:30
      Tutorials & Competition

      Interactive Google Colab Maze environment; implementing Bellman updates, comparing SARSA vs Q-Learning.

      Go to contribution page
    5. 24. Keynote 1: Designing for Intelligence: Particle Accelerators in the AI Era (KEY-01)
      Verena Kain (CERN, Switzerland)
      16/09/2026, 17:30
      Keynotes

      Real-time beam steering, AWAKE electron beam stabilization, and safety constraints at CERN.

      Go to contribution page
    6. 6. Lecture 3: Policy Gradients and Actor Critics (LEC-03)
      Thomas Gallien (JOANNEUM RESEARCH / AI Austria)
      17/09/2026, 09:00
      Lectures

      Continuous state spaces, policy parameterization pi_theta(a|s), REINFORCE, Advantage Actor-Critic, and PPO.

      Go to contribution page
    7. 7. Keynote 2: What Should Models Model in Model-Based RL? (KEY-02)
      Michael Bowling (University of Alberta / Amii, Canada)
      17/09/2026, 09:45
      Keynotes

      Continual learning, game-theoretic foundations, world models, predictive representations.

      Go to contribution page
    8. 8. Keynote 3: The Benefits of Satisficing in Reinforcement Learning (KEY-03)
      Ronald Ortner (Montanuniversität Leoben, Austria)
      17/09/2026, 11:00
      Keynotes

      MDP regret bounds, PAC learning, satisficing sequential decision making.

      Go to contribution page
    9. 23. Keynote 4: Learning Humanoid Robot Policies for Industrial Tasks (KEY-04)
      Elmar Rückert (Montanuniversität Leoben - CPS, Austria)
      17/09/2026, 11:45
      Keynotes

      Stochastic optimal control, dynamic movement primitives, sim-to-real transfer, humanoid robotics.

      Go to contribution page
    10. 17. Tutorial 2: Air Traffic Control as an MDP (Intermediate) (TUT-02)
      Leander Grech (Paris Lodron Universität Salzburg (PLUS))
      17/09/2026, 14:00
      Tutorials & Competition

      MDP formulation for air traffic management, multi-aircraft continuous state spaces, first trained agent vs baseline in Flight4DEnv.

      Go to contribution page
    11. 19. Tutorial 3: The Flight Challenge: How to Compete (Advanced Tournament) (TUT-03)
      Leander Grech (Paris Lodron Universität Salzburg (PLUS))
      17/09/2026, 16:00
      Tutorials & Competition

      Air Traffic Control Tournament in Flight4DEnv; custom rewards, safe separation minimums, live leaderboard.

      Go to contribution page
    12. 20. Interactive Wrap-Up Tutorial: Findings & Expert Panel (TUT-04)
      Leander Grech (Paris Lodron Universität Salzburg (PLUS)), Olga Mironova (Paris Lodron Universität Salzburg (PLUS) / IDA Lab), Simon Hirlaender (Paris Lodron Universität Salzburg (PLUS) / IDA Lab), Thomas Gallien (JOANNEUM RESEARCH / AI Austria)
      18/09/2026, 09:00
      Tutorials & Competition

      Flight Challenge championship debrief, strategy evaluation, open audience Q&A with keynote speakers.

      Go to contribution page
    13. 21. Lecture 4: Agentic AI in the Context of Reinforcement Learning (LEC-04)
      Jonas Dauer (German Aerospace Center (DLR)), Marius-Constantin Dinu (ExtensityAI / AI Austria)
      18/09/2026, 11:00
      Lectures

      Token-level MDPs, verifiable execution loops, LLM agents with RL environments, tool use and reflection. Includes 5-min Lightning Pitch: DLR LUMEN Rocket Propulsion RL Benchmark (Jonas Dauer, DLR Lampoldshausen).

      Go to contribution page
    14. 22. Tournament Final, Awards Ceremony & Closing Remarks (CLOSE)
      Leander Grech (Paris Lodron Universität Salzburg (PLUS)), Olga Mironova (Paris Lodron Universität Salzburg (PLUS) / IDA Lab), Simon Hirlaender (Paris Lodron Universität Salzburg (PLUS) / IDA Lab)
      18/09/2026, 12:00
      Tutorials & Competition

      Announcement of winners (3x Sutton & Barto textbook prizes), certificate distribution, and Bootcamp 2027 outlook.

      Go to contribution page