Reinforcement Learning

Recent and popular advances in Reinforcement Learning are known to be data-hungry. Attempts to handle this deficit include developing complex simulators while improving the sim2real transition of models, explicitly modelling the environment, or leveraging available offline data.

Research feed

Episode-based RL with Movement Primitive

Maximilian Hüttenrauch, AI Researcher at appliedAI Institute, talks about episode-based reinforcement learning with movement primitive.

Double Gumbel Q-learning

David Yu-Tung Hui, MILA, will talk about his work presented at NeurIPS 2023, Double Gumbel Q-Learning, a Deep Q-Learning algorithm …

Hyperparameters in Reinforcement Learning and How To Tune Them

Finding good hyperparameters for reinforcement learning (RL) is a notoriously difficult task. Instead of luck or grid search, one can apply …

Tianshou: An elegant deep reinforcement learning library

Tianshou is a deep reinforcement learning library based on pure PyTorch. It caters to the needs of researchers and practitioners alike by …

Exploiting past success in Off-Policy Actor-Critic

Extracting knowledge from previously gathered data is the very core of exploitation in reinforcement learning (RL). During training, a …

Jump-Start Reinforcement Learning

Reinforcement learning often presents a challenge when training an agent from scratch, as reward sparsity and exploration issues can impede …

Implicit Q Learning

A core challenge when applying dynamic programming based approaches to offline reinforcement learning is the bootstrapping error. This pill …

Safe and efficient deep reinforcement learning

This 2-day dive into deep RL for decision and control is suitable for engineers who want to solve real-world control problems with efficient …

Classical and modern methods in planning and control

A review of model-based planning and control for engineers interested in solving real-world decision and control problems with efficient …

Advantage-Induced Policy Alignment

Building on the classic results on reward weighted regression and its more recent adaptation to deep learning, a new algorithm called …

Critic Regularized Regression

A simple but powerful algorithm for offline reinforcement learning, which can be seen as a combination of behavior cloning and Q-learning, …

Deep Reinforcement Learning at the Edge of the Statistical Precipice

A sound statistical analysis of the performance of RL algorithms is performed, with outcomes that force a reconsideration of the ranking of …

Other series in Advances and fundamentals in ML

Simulation and AI

AI techniques are fundamentally transforming the field of simulation by combining physics-based modeling with data-driven machine learning.

Diffusion Models

Diffusion models (DM) have become the state of the art for sample quality in generative modelling. They work by sequentially corrupting …

Geometric deep learning

Specialized deep learning architectures exploit the intrinsic regularities arising from the underlying structure of the physical world. …