DeepHack.RL: Tejas Kulkarni - Revisiting successor representations
Deep reinforcement learning with intrinsic motivation and temporal abstractions
DeepHack.RL: Mikhail Burtsev - Model-based reinforcement learning for alternating environments
The Successor Representation: Its Computational Logic and Neural Substrates
State Representation Learning for Goal-Conditioned Reinforcement Learning – talk – PRL @ ICAPS 2022
Tejas Kulkarni | 2016 kayak reel
Session 1: Reinforcement Learning
Ganita-Sastram by Sri.Tejas Kulkarni
Our Ten-year journey
2D mountain car with random actions
Learning State Representations - Yael Niv - NIPS (NeurIPS) 2017
[PreReg@NeurIPS'20] (69) Policy Agnostic Successor Features
Ben Eysenbach Thesis Defense
Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments
Successor Features 4x4 grid 4 task-items
Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning
Predictive Maps in the Brain
Predictive State Representation
A neurally plausible model learns successor representations in partially observable environments
Successor Representation for Reinforcement Learning, Timur Garipov, bayesgroup.ru
Семинар 6. Процесс формирования Successor Features с помощью Distributed Hebbian Temporal Memory
[MIND 2018] Ida Momennejad: Predictive Representations Tutorial
Learning Fast with No Goals - VISR Explained
The hippocampus as a predictive map
The Surprising Effectiveness of Representation Learning for Visual Imitation
![[PreReg@NeurIPS'20] (69) Policy Agnostic Successor Features](https://img.youtube.com/vi/DgBJ4zYHBeE/0.jpg)
![[MIND 2018] Ida Momennejad: Predictive Representations Tutorial](https://img.youtube.com/vi/9jjSFtyyhnQ/0.jpg)
