Research Notebook
Reading papers, documenting ideas, implementing algorithms, and developing research insights in Reinforcement Learning, Graph Neural Networks, Intelligent Systems, and Artificial Intelligence.
Human-level Control Through Deep Reinforcement Learning
Volodymyr Mnih et al. • Nature, 2015
Introduce Deep Q Networks, explain the motivation, architecture, algorithm, implementation, limitations, and future research directions.
Research Papers
6Graph Convolutional Networks
Thomas N. Kipf, Max Welling • ICLR, 2017
GCN from First Principles.
Double DQN: Reducing Overestimation Bias
Hado van Hasselt et al. • AAAI, 2016
Reducing Overestimation Bias in Deep Q-Networks.
Prioritized Experience Replay
Tom Schaul et al. • ICLR, 2016
Improving Sample Efficiency by prioritizing important transitions.
Graph Attention Networks
Petar Veličković et al. • ICLR, 2018
Understanding GAT and attention mechanisms in graph structures.
Rainbow DQN
Matteo Hessel et al. • AAAI, 2018
Combining Multiple DQN Improvements into a single state-of-the-art agent.
Proximal Policy Optimization
John Schulman et al. • OpenAI, 2017
Understanding PPO: A robust and simple policy gradient algorithm.
Implementation Notes
1Literature Reviews
2Trustworthy Artificial Intelligence
Multiple Authors • Various, 2026
Core Concepts of interpretability, robustness, and fairness.
Multi-Agent Reinforcement Learning
Multiple Authors • Various, 2026
Introduction to MARL paradigms and challenges.
Research Ideas
1Reading List
5Graph Convolutional Networks
Thomas N. Kipf, Max Welling • ICLR, 2017
GCN from First Principles.
Double DQN: Reducing Overestimation Bias
Hado van Hasselt et al. • AAAI, 2016
Reducing Overestimation Bias in Deep Q-Networks.
Rainbow DQN
Matteo Hessel et al. • AAAI, 2018
Combining Multiple DQN Improvements into a single state-of-the-art agent.
Trustworthy Artificial Intelligence
Multiple Authors • Various, 2026
Core Concepts of interpretability, robustness, and fairness.
Multi-Agent Reinforcement Learning
Multiple Authors • Various, 2026
Introduction to MARL paradigms and challenges.
Bookmarks
2Human-level Control Through Deep Reinforcement Learning
Volodymyr Mnih et al. • Nature, 2015
Introduce Deep Q Networks, explain the motivation, architecture, algorithm, implementation, limitations, and future research directions.
Understanding DQN Architecture
Rikesh Yadav • Research Notes, 2026
A deep dive into the CNN architecture used in Deep Q-Networks.
Recently Read
2Understanding DQN Architecture
Rikesh Yadav • Research Notes, 2026
A deep dive into the CNN architecture used in Deep Q-Networks.
Proximal Policy Optimization
John Schulman et al. • OpenAI, 2017
Understanding PPO: A robust and simple policy gradient algorithm.