Program Schedule

Detailed agenda for the 2nd Reinforcement Learning Bootcamp

View Schedule Meet the Speakers

Program Overview

A comprehensive look at our three-day event

Our program is designed to provide a comprehensive introduction to reinforcement learning, from basic concepts to advanced applications. The bootcamp spans three full days, with a mix of theoretical lectures, hands-on workshops, and networking opportunities.

Schedule

Detailed agenda for September 17-19, 2025

Day 1: Wednesday, September 17

11:00 - 13:00	Coffee and Arrival
13:00 - 14:00	Lunch Break
14:00 - 15:00	Opening and Introduction
15:00 - 16:00	Lecture 0 I - Introduction to Reinforcement Learning
16:00 - 17:00	Lecture 0 II - RL Fundamentals
17:00 - 18:00	Coffee Break
18:00 - 19:00	Keynote: Prof. Sergey Levine (UC Berkeley) - "Recent Advances in Deep Reinforcement Learning"
19:30 - 21:00	Social Opening Event & Networking Reception

Day 2: Thursday, September 18

9:30 - 10:15	Keynote: Prof. Peter Auer (University of Leoben) - "Multi-Armed Bandits and Exploration Strategies"
10:15 - 11:00	Keynote: Dr. Samuele Tosatto (University of Innsbruck) - "Policy Optimization in Reinforcement Learning"
11:00 - 11:45	Coffee Break
11:45 - 12:30	Keynote: Emerging Researcher - "Frontier Topics in Reinforcement Learning"
12:30 - 13:30	Lunch Break
13:30 - 14:30	Policy Gradients and Actor Critics I
14:30 - 15:00	Break
15:00 - 16:00	Policy Gradients and Actor Critics II
16:00 - 16:30	Coffee Break
16:30 - 18:30	Hands-on Workshop: "Implementing PPO from Scratch"
19:00 - 21:00	Social Event

Day 3: Friday, September 19

9:30 - 11:00	Hands-on Workshop
11:00 - 11:45	Coffee Break
11:45 - 12:30	SOTA
12:30 - 13:30	Lunch Break
13:30 - 15:00	Final Round and Closing Remarks
15:00 - 17:00	Salzburg Visit

Speakers

Meet our expert speakers and instructors

Prof. Sergey Levine

UC Berkeley

Pioneering researcher in deep reinforcement learning and robotic control

Prof. Peter Auer

University of Leoben

Leading expert in multi-armed bandits and exploration strategies

Dr. Samuele Tosatto

University of Innsbruck

Specialist in policy optimization for reinforcement learning

Emerging Researcher

To Be Announced

Cutting-edge research in frontier areas of reinforcement learning

Workshops & Deep Lectures

Intensive learning experiences combining theory and practice

Setting Up Your RL Environment

Configure Python environments with PyTorch, TensorFlow, and Gymnasium for state-of-the-art RL experimentation.

Implementing PPO from Scratch

Build a Proximal Policy Optimization algorithm implementation step-by-step, with detailed code walkthroughs.

Building World Models for RL

Learn to create and train neural network models of environments to improve sample efficiency in RL training.

Multi-Agent Systems Implementation

Design and implement collaborative and competitive multi-agent reinforcement learning systems.

Advanced Policy Gradient Methods

In-depth exploration of state-of-the-art policy optimization techniques including PPO, TRPO, and SAC.

Model-Based Reinforcement Learning

Comprehensive review of model-based RL approaches, from Dyna-Q to modern deep learning architectures.

Multi-Agent Reinforcement Learning

Theoretical foundations and practical implementations of MARL algorithms, coordination mechanisms, and emergent behaviors.