I am a robotics engineer and an incoming PhD student at the Intelligent Autonomous Systems group at TU Darmstadt. I am interested in the fields of robotics, reinforcement learning, imitation learning, and decision-making in partially observable and multi-agent settings.

I received my MSc. in Robotics with cum laude honours from TU Delft where I worked on generative imitation learning techniques under the supervision of Prof. Jens Kober. In the past, I have held research positions in graph-based ML at the Robert Bosch Center For Data Science & AI at IIT Madras and have also interned in multi-agent coordination at Bosch Research.

In my spare time, I love photography and music. I also run an academic blog where I share archives of my lecture notes, paper summaries, and misc. ideas on robotics/ML.

Email: anishhdiwan@gmail.com

Socials: LinkedIn | GitHub | Notes

news

Jan 26, 2025	I will soon start my PhD in robot learning at IAS, TU Darmstadt!
Jan 22, 2025	My MSc. thesis was accepted at ICLR 2025
Sep 19, 2024	I graduated MSc. Robotics from TU Delft with cum laude! 🎓

selected publications

1. 

   Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation

   Anish Abhijit Diwan, Julen Urain, Jens Kober, and Jan Peters

   In International Conference on Learning Representations (ICLR), 2025

   Paper accepted. Jens Kober and Jan Peters supervised equally.

   Abs arXiv Website

   This paper introduces a new imitation learning framework based on energy-based generative models capable of learning complex, physics-dependent, robot motion policies through state-only expert motion trajectories. Our algorithm, called Noise-conditioned Energy-based Annealed Rewards (NEAR), constructs several perturbed versions of the expert’s motion data distribution and learns smooth, and well-defined representations of the data distribution’s energy function using denoising score matching. We propose to use these learnt energy functions as reward functions to learn imitation policies via reinforcement learning. We also present a strategy to gradually switch between the learnt energy functions, ensuring that the learnt rewards are always well-defined in the manifold of policy-generated samples. We evaluate our algorithm on complex humanoid tasks such as locomotion and martial arts and compare it with state-only adversarial imitation learning algorithms like Adversarial Motion Priors (AMP). Our framework sidesteps the optimisation challenges of adversarial imitation learning techniques and produces results comparable to AMP in several quantitative metrics across multiple imitation settings.