harsha kokel

  • CV
  • Linked In
  • Github
  • Mail
  • Twitter
  1. Tags »

  2. RL

    • Browse tags
  • Apr 22, 2020 planning  abstractions  RL 

    Learning Symbolic Representations for planning

    In the pursuit of learning planner from data, I ended up reading Konidaris et al. (JAIR 2018). Getting through this paper was an onerous task. Which I would not like to do again. So, here are my notes on the key concepts from that paper, which are relevant for learning high-level, abstract planner.

  • Apr 15, 2020 RL  GNN  neurosymbolic  relational 

    Deep Relational RL

    Relational RL has not made a lot of splashes in real-world because it is easier to write a planner than learn a relational RL agent. This might be about to change with the current achievements of the graph based relational reasoning approaches. This article summarizes my understanding of the pioneering work of Vinicius Zambaldi et al. (ICLR 2019) on Deep Relational RL.

  • Apr 12, 2020 RL  relational  SRL 

    Relational Reinforcement Learning

    My notes on Džeroski, Sašo, Luc De Raedt, and Kurt Driessens, Machine Learning 2001

  • Mar 20, 2020 RL 

    Hindsight Experience Replay

    My notes on Marcin Andrychowicz et al. NeurIPS 2017.

  • Mar 18, 2020 RL  imitation  generalization 

    Logical Program Policies

    My notes on Tom Silver, Kelsey R. Allen, Alex K. Lew, Leslie Kaelbling, and Josh Tenenbaum, AAAI 2020.

  • Dec 6, 2019 RL  offline  summary 

    Fitted Q and Batch Reinforcement Learning

    Some pointers on Batch Reinforcement Learning and Fitted Q. These were gathered while working on an RL for healthcare project, as part of Advanced RL course by Prof. Sriraam Natarajan.

  • Oct 28, 2019 RL  hierarchy  coursework 

    Hierarchical Reinforcement Learning

    An overview of Hierarchical RL. Written as part of Advanced RL course by Prof. Sriraam Natarajan.

  • Oct 5, 2019 RL  advice  starling 

    Active Advice Seeking for Inverse Reinforcement Learning

    My notes on Phillip Odom and Sriraam Natarajan, AAMAS 2016.

  • Sep 3, 2019 planning  XAI  RL 

    Minimal Sufficient Explanation

    My notes on Omar Zia Khan, Pascal Poupart, and James P Black, ICAPS 2009

hk

  • Homepage
  • Publications
  • BLOG POSTS
miscellaneous

Powered by Hugo and design by HTML5 UP.