MRC Club - AgentLab Reading Group Archive

Must-Read-Classics (MRC) for Machine Learning Researchers

Subscribe to the mailling list (Open to public)

Location: Pankhurst Building

Time: 2 PM to 4 PM, Every Friday

Papers

Date	Paper
28 Feb 2025	Adam: A Method for Stochastic Optimization
7 Mar 2025	Attention Is All You Need
14 Mar 2025	Proximal Policy Optimization Algorithms
21 Mar 2025	Mastering the game of Go with deep neural networks and tree search
28 Mar 2025	Denoising Diffusion Probabilistic Models
2 May 2025	Highly accurate protein structure prediction with AlphaFold
9 May 2025	A Natural Policy Gradient
23 May 2025	Covariant Policy Search
30 May 2025	Guided Policy Search
6 June 2025	Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
13 June 2025	Trust Region Policy Optimization
27 June 2025	Maximum a Posteriori Policy Optimisation
28 Nov 2025	Approximately Optimal Approximate RL
5 Dec 2025	Mirror Descent Policy Optimization
16 Jan 2026	Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
23 Jan 2026	Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO
27 Feb 2026	Muesli: Combining Improvements in Policy Optimization
—	Human-level control through deep reinforcement learning
—	Mastering Atari, Go, chess and shogi by planning with a learned model
—	BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
—	Score-Based Generative Modeling through Stochastic Differential Equations
—	Elucidating the Design Space of Diffusion-Based Generative Models
—	Associative Recurrent Memory Transformer

Books

Date	Book
4 Apr 2025	Reinforcement Learning: An Introduction – Chapter 13
11 Apr 2025	Reinforcement Learning: An Introduction – Chapter 6
25 Apr 2025	Reinforcement Learning: An Introduction – Chapters 7 & 8
4 Jul 2025	Numerical Optimization – Chapter 3
11 Jul 2025	Numerical Optimization – Chapter 4
18 Jul 2025	Probabilistic Machine Learning: An Introduction – Chapter 6
—	Machine Learning – A Probabilistic Perspective
—	Deep Learning