Arnav Kumar Jain's repositories
Eta_Psi_Learning
Codebase of ηψ-Learning algorithm that learns a non-Markovian maximum state entropy exploration policy by combining predecessor and successor representation to estimate the state visitation distribution of a trajectory of finite length.
cwvae
Clockwork Variational Autoencoder
deep_bisim4control
Learning Invariant Representations for Reinforcement Learning without Reconstruction
dream
Decoupled Reward-free ExplorAtion and Execution for Meta-reinforcement learning
dreamerv2
Mastering Atari with Discrete World Models
gen-efficientnet-pytorch
Pretrained EfficientNet, MixNet, MobileNetV3, MNASNet A1 and B1, FBNet, Single-Path NAS
impact-driven-exploration
impact-driven-exploration
IQ-Learn
(NeurIPS '21 Spotlight) IQ-Learn: Inverse Q-Learning for Imitation
metaworld
An open source robotics benchmark for meta- and multi-task reinforcement learning
progressive_growing_of_gans
Progressive Growing of GANs for Improved Quality, Stability, and Variation
progressive_growing_of_gans_tf
TensorFlow Re-implementation of Progressive Growing of GANs for Improved Quality, Stability, and Variation
RepDistiller
Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods
robocup-stp
STP Architecture
skip-thoughts
An implementation of Skip-Thought Vectors in PyTorch
tdmpc
Code for "Temporal Difference Learning for Model Predictive Control"
varibad
Implementation of VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning - Zintgraf et al. (ICLR 2020)