ondrejbiza
PhD student in Deep Learning and Robotics at Northeastern University.
Northeastern UniversityBoston, MA, USA
Pinned Repositories
aamas_19
Source code for the paper "Online Abstraction with MDP Homomorphisms for Deep Learning".
action_attention_iclr_22
Source code for "Binding Actions to Objects in World Models. Ondrej Biza, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong and Thomas Kipf. ICLR 2022 workshop on Objects, Structure and Causality."
action_priors
Source code for Action Priors for Large Action Spaces in Robotics. Biza, Wang, Platt, van de Meent, Wong. AAMAS'21.
bandits
Comparison of bandit algorithms from the Reinforcement Learning bible.
bi-att-flow
Bidirectional Attention Flow
discrete_abstractions
Source code for Learning Discrete State Abstractions With Deep Variational Inference. Biza, Platt, van de Meent, Wong. AABI'21. https://arxiv.org/abs/2003.04300
machine_intelligence_course
Tensorflow tutorials.
negative-sampling-icml-21
Original source code for "The Impact of Negative Sampling on Contrastive Structured World Models. O Biza, E van der Pol, T Kipf. ICML'21 SSL workshop."
racetrack
An environment for tabular Reinforcement Learning agents.
tf_calibrate
Calibration of neural networks in Tensorflow.
ondrejbiza's Repositories
ondrejbiza/action_priors
Source code for Action Priors for Large Action Spaces in Robotics. Biza, Wang, Platt, van de Meent, Wong. AAMAS'21.
ondrejbiza/action_attention_iclr_22
Source code for "Binding Actions to Objects in World Models. Ondrej Biza, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong and Thomas Kipf. ICLR 2022 workshop on Objects, Structure and Causality."
ondrejbiza/aamas_19
Source code for the paper "Online Abstraction with MDP Homomorphisms for Deep Learning".
ondrejbiza/negative-sampling-icml-21
Original source code for "The Impact of Negative Sampling on Contrastive Structured World Models. O Biza, E van der Pol, T Kipf. ICML'21 SSL workshop."
ondrejbiza/discrete_abstractions
Source code for Learning Discrete State Abstractions With Deep Variational Inference. Biza, Platt, van de Meent, Wong. AABI'21. https://arxiv.org/abs/2003.04300
ondrejbiza/bisim_metric
ondrejbiza/c-swm
Contrastive Learning of Structured World Models
ondrejbiza/relational_ndf
ondrejbiza/vae
Variational autoencoders implemented in Tensorflow.
ondrejbiza/baby-a3c
A high-performance Atari A3C agent in 180 lines of PyTorch
ondrejbiza/bmg
Bayesian mixture of Gaussians
ondrejbiza/cem
ondrejbiza/feudal-rl
ondrejbiza/fewshot
ondrejbiza/geom_cloning_corl_23
ondrejbiza/google-research
Google Research
ondrejbiza/helping_hands_website
ondrejbiza/hmm
Hidden Markov Models.
ondrejbiza/invariant_slot_attention.github.io
ondrejbiza/ondrejbiza.github.io
My personal website.
ondrejbiza/pgm
Exercises from the Probabilistic Graphical Models: Principles and Techniques book.
ondrejbiza/pytorch-maml-rl
Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch
ondrejbiza/se3-transformer-public
code for the SE3 Transformers paper: https://arxiv.org/abs/2006.10503
ondrejbiza/shapewarping
ondrejbiza/so3_examples
ondrejbiza/sonnet
TensorFlow-based neural network library
ondrejbiza/SPACE
Official PyTorch implementation of "SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition"
ondrejbiza/stable-baselines
A fork of OpenAI Baselines, implementations of reinforcement learning algorithms
ondrejbiza/sunds
ondrejbiza/taxpose
TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulation