Apply now
Postgraduate DiplomaData, AI, Simulation & Analytics Applications open

Diploma in Classical and Deep RL for Dynamic Systems

Online postgraduate diploma of 800 hours in classical and deep reinforcement learning for dynamic systems. 8 modules covering Markov decision processes, tabular methods, function approximation, value-based deep RL, policy gradient and actor-critic, model-based RL and sim-to-real transfer in line with ISO/IEC 22989:2022, ISO/IEC 23053:2022 and IEC 61508:2010, with an assigned technical tutor.

Duration6–8 months
ModeOnline
LanguageEnglish
Start datesSet by the faculty
AwardSEIUM Institute diploma
Enrol now View syllabus Ask an advisor
Virtual lab · try it before you enrol

Take the controls.

Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.

SIM · LIVE ●
Learning outcomes

What you will be able to do

01

Model dynamic systems as Markov decision processes.

02

Implement tabular temporal-difference and Monte Carlo methods.

03

Apply function approximation and deep networks to value learning.

04

Train actor-critic agents in continuous action spaces.

05

Integrate learned dynamic models into planning and control.

06

Design simulation-to-real transfer strategies.

07

Evaluate agents with reproducible metrics and safety criteria.

Profile

Who it's for

  • Reinforcement learning engineers.
  • Intelligent control engineers looking beyond classical PID and MPC.
  • Robotics researchers.
  • Data scientists working in optimisation.
  • Autonomous systems engineers.
  • Simulation developers.
  • Engineering or science graduates seeking to enter industrial robotics.
Standards & tools

What you'll work with

  • ISO/IEC 22989:2022 (AI concepts and terminology)
  • ISO/IEC 23053:2022 (Framework for AI systems using machine learning)
  • IEC 61508:2010 (Functional safety of E/E/PE safety-related systems)
  • ISO 26262:2018 (Road vehicles: functional safety)
  • Regulation (EU) 2024/1689 (EU Artificial Intelligence Act)
  • ISO/IEC 23894:2023 (AI risk management)
  • IEC 61131-3:2013 (PLC programming languages)
  • Gymnasium
  • Stable-Baselines3
  • MuJoCo
  • Ray RLlib
  • NVIDIA Isaac Lab
Syllabus

8 modules

  1. 1.1States, actions, rewards and transitions
  2. 1.2Discounted return and horizon
  3. 1.3Bellman equations for value and action-value
  4. 1.4Value iteration and policy iteration
  5. 1.5Dynamic programming and contraction
  6. 1.6Partially observable MDPs and belief states
  7. 1.7Discretisation of continuous dynamic systems
  8. 1.8Reward function design
  9. 1.9Relationship with LQR optimal control
  10. 1.10Workshop: inverted pendulum solved by dynamic programming
  1. 2.1Monte Carlo policy evaluation
  2. 2.2Temporal differences TD(0) and TD(lambda)
  3. 2.3Eligibility traces
  4. 2.4SARSA and on-policy control
  5. 2.5Q-learning and off-policy control
  6. 2.6Epsilon-greedy and softmax exploration
  7. 2.7Double Q-learning and maximisation bias
  8. 2.8Dyna-Q and model-based planning
  9. 2.9Convergence and Robbins-Monro conditions
  10. 2.10Lab: Q-learning on discretised MountainCar
  1. 3.1Linear approximation and basis functions
  2. 3.2Tile coding and Fourier bases
  3. 3.3Semi-gradient TD with linear approximation
  4. 3.4The deadly triad of instability
  5. 3.5Least-squares TD and LSPI
  6. 3.6Neural networks as approximators
  7. 3.7Normalisation of observations and rewards
  8. 3.8Generalisation across states
  9. 3.9Hyperparameter tuning and seeds
  10. 3.10Practical exercise: CartPole control with linear approximation
  1. 4.1Deep Q-Network and experience replay
  2. 4.2Target networks and stabilisation
  3. 4.3Double DQN and Dueling DQN
  4. 4.4Prioritised experience replay
  5. 4.5Rainbow and combining improvements
  6. 4.6Distributional RL: C51 and QR-DQN
  7. 4.7Exploration with parametric noise
  8. 4.8Discrete actions in physical systems
  9. 4.9Diagnosing learning curves
  10. 4.10Lab: DQN with Stable-Baselines3
  1. 5.1Policy gradient theorem and REINFORCE
  2. 5.2Baselines and variance reduction
  3. 5.3Actor-critic A2C and A3C
  4. 5.4Generalised advantage estimation (GAE)
  5. 5.5TRPO and trust regions
  6. 5.6PPO with ratio clipping
  7. 5.7DDPG for continuous actions
  8. 5.8TD3 and critic overestimation
  9. 5.9Soft Actor-Critic and maximum entropy
  10. 5.10Lab: SAC on a robotic arm in MuJoCo
  1. 6.1Learning dynamic models with neural networks
  2. 6.2PETS probabilistic ensembles
  3. 6.3Model predictive control with a learned model
  4. 6.4MBPO and short rollouts
  5. 6.5World models and Dreamer
  6. 6.6System identification versus learned models
  7. 6.7Compounding error and planning horizon
  8. 6.8Sample efficiency in real systems
  9. 6.9Combining physics and data
  10. 6.10Practical exercise: quadrotor control with a learned model
  1. 7.1The reality gap in dynamics and sensors
  2. 7.2Domain randomisation of physical parameters
  3. 7.3Parameter identification and calibration
  4. 7.4Offline RL with CQL and IQL
  5. 7.5Safety when deploying on hardware
  6. 7.6Delays, noise and actuator saturation
  7. 7.7Gymnasium and Isaac Lab environments
  8. 7.8Evaluation and reproducible benchmarks
  9. 7.9AI regulation and functional safety
  10. 7.10Case study: temperature control of a thermal process
  1. 8.1System selection and MDP formulation
  2. 8.2Building the simulation environment
  3. 8.3Reward and constraint design
  4. 8.4Training baseline agents
  5. 8.5Comparison of algorithms and seeds
  6. 8.6Robustness analysis against disturbances
  7. 8.7Hardware transfer plan
  8. 8.8Reproducible documentation of the experiment
  9. 8.9Report and presentation
  10. 8.10Final project: final review with the tutor
Methodology, software & labs

How you'll learn

100% online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within each intake, so the programme is compatible with work.

Each module combines theory, guided reading of the original standard and applied exercises. The working software is Gymnasium, Stable-Baselines3, MuJoCo, Ray RLlib and NVIDIA Isaac Lab, in free, academic or evaluation versions. Practical work is based on real procedures for control of pendulums and underactuated systems in simulation, tuning of thermal process controllers and simulated robotic locomotion and manipulation. Assessment is continuous by module plus the final project.

Standards covered: ISO/IEC 22989:2022, ISO/IEC 23053:2022, IEC 61508:2010, ISO 26262:2018, Regulation (EU) 2024/1689, ISO/IEC 23894:2023, IEC 61131-3:2013.

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of ISO/IEC 22989:2022, ISO/IEC 23053:2022 and IEC 61508:2010 applied to real cases, not as a theoretical annex.
Industry software:Gymnasium, Stable-Baselines3, MuJoCo, Ray RLlib and NVIDIA Isaac Lab, in free, academic or evaluation versions.
Final project:an RL controller for a real dynamic system, from MDP formulation and simulation environment to algorithm comparison, robustness analysis and hardware transfer plan, reviewed by your tutor.
Flexible format:100% online, no fixed timetables, compatible with full-time work.
Capstone project

Build it end to end

Your final project follows the real engineering workflow, step by step, reviewed by your tutor.

System and MDP
Select a dynamic system and formulate it as a Markov decision process.
Simulation environment
Build the Gymnasium environment with reward and constraint design.
Agent training
Train baseline agents such as PPO and SAC and compare algorithms across seeds.
Robustness analysis
Test the agents against disturbances and domain randomisation.
Final project
Present the hardware transfer plan with reproducible documentation, reviewed by your tutor.
Career opportunities

Where this takes you

Reinforcement learning engineerIntelligent control engineerRobotics researcherOptimisation data scientistAutonomous systems engineerSimulation developer
Admissions & scholarships

Requirements

  • Prior technical training or professional experience in the sector. No university degree is required.
  • Internet connection and a computer capable of running the programme software.
  • English sufficient to read technical standards.

Ready to start?

Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.

Apply now Scholarships
FAQ

Frequently asked questions

The programme totals 800 hours over 6–8 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.

You work with Gymnasium, Stable-Baselines3, MuJoCo, Ray RLlib and NVIDIA Isaac Lab, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.

A SEIUM Institute diploma, awarded on passing the continuous assessment and the final project. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.

Yes. Modules passed are recognised in a higher programme in the same area (postgraduate diploma or master's). Ask about the recognition policy when you enrol.

Prior technical training or professional experience in the sector (no university degree required), a computer able to run the programme software and English sufficient to read technical standards.

Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.

Keep exploring

Related programmes

See all in Data, AI, Simulation & Analytics
Postgraduate Diploma2,000 $

Diploma in Network Operation Forecasting/Optimization

Online postgraduate diploma of 800 hours in grid operation forecasting and optimisation: 8 modules covering power system operation under Regulation (EU) 2017/1485, demand forecasting, renewable generation…

6–8 monthsOnlineData, AI, Simulation & Analytics
Postgraduate Diploma2,000 $

Diploma in Privacy, Traceability and Applied Ethics

Online postgraduate diploma of 800 hours in privacy, traceability and applied ethics: 8 modules covering privacy and data protection, privacy by design, impact assessments, data and…

6–8 monthsOnlineData, AI, Simulation & Analytics
Postgraduate Diploma1,220 $

Diploma in Stateful and Exactly-Once Pipeline Design

Online postgraduate diploma of 800 hours in stateful and exactly-once pipeline design. 8 modules covering processing semantics, state management, checkpoints and recovery, end-to-end transactions, event time…

800 hours · 6–8 monthsOnlineData, AI, Simulation & Analytics
Diploma in Classical and Deep RL for Dynamic SystemsEnrol
Related programmes

More in Data, AI, Simulation & Analytics

Diploma in Validation with Real Data and Gap BridgingView programme →Diploma in Integration of Technical Assistants in OperationsView programme →Diploma in Privacy, Traceability and Applied EthicsView programme →Diploma in Graph Analytics Pipeline ProductionView programme →Diploma in Parallelization with CUDA/OpenMP and ProfilingView programme →Diploma in Dataset Generation and Realism MetricsView programme →

All Data, AI, Simulation & Analytics programmes → · How to apply · Fees & financing · Scholarships

Scroll to Top
SEIUM – Institute of Advanced Engineering
Powered by  GDPR Cookie Compliance
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.