arjunchandra
Dad. Expanding collective potential at Brua IO. Lead large model training stability at Graphcore. Examining the AI quest.
Brua IOOslo, Norway
Pinned Repositories
accelerate
A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
arjunchandra.github.io
Log of views and explanations
baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
BCQ
PyTorch implementation of BCQ for "Off-Policy Deep Reinforcement Learning without Exploration"
brain-tokyo-workshop
🧠🗼
c-swm
Contrastive Learning of Structured World Models
C51-DDQN-Keras
C51-DDQN in Keras
caffe
Caffe: a fast open framework for deep learning.
DeepRLHacks
Hacks for training RL systems from John Schulman's lecture at Deep RL Bootcamp (Aug 2017)
wildrl
Scaling RL to go wild.
arjunchandra's Repositories
arjunchandra/talk-transcripts
Transcripts of Clojure-related talks
arjunchandra/dlbook_notation
LaTeX files for the Deep Learning book notation
arjunchandra/turicreate
Turi Create simplifies the development of custom machine learning models.
arjunchandra/paac
Open source implementation of the PAAC algorithm presented in Efficient Parallel Methods for Deep Reinforcement Learning
arjunchandra/C51-DDQN-Keras
C51-DDQN in Keras
arjunchandra/safe_learning
Safe reinforcement learning with stability guarantees
arjunchandra/carnd
Projects during the Self-Driving Car Engineer Nanodegree program from Udacity
arjunchandra/treeagent
Decision tree ensembles as RL policies
arjunchandra/solar_panels_rl
Repository for code experimenting with RL and Solar Tracking
arjunchandra/baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
arjunchandra/DeepRLHacks
Hacks for training RL systems from John Schulman's lecture at Deep RL Bootcamp (Aug 2017)
arjunchandra/osim-rl
Reinforcement learning environments with musculoskeletal models
arjunchandra/seq2seq-signal-prediction
Signal prediction with a seq2seq RNN model in TensorFlow
arjunchandra/deep-rl-tensorflow
TensorFlow implementation of Deep Reinforcement Learning papers
arjunchandra/dnc
A TensorFlow implementation of the Differentiable Neural Computer.
arjunchandra/mxnet
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
arjunchandra/qbsolv
qbsolv is a metaheuristic or partitioning solver that solves a potentially large quadratic unconstrained binary optimization (QUBO) problem by splitting it into pieces that are solved either on a D-Wave system or via a classical tabu solver.
arjunchandra/cozmo-python-sdk
Anki Cozmo Python SDK
arjunchandra/nips2015_vrnn
arjunchandra/cle
arjunchandra/requests-for-research
A living collection of deep learning problems
arjunchandra/imitation
arjunchandra/reinforcejs
Reinforcement Learning Agents in Javascript (Dynamic Programming, Temporal Difference, Deep Q-Learning, Stochastic/Deterministic Policy Gradients)
arjunchandra/tensorflow-deepq
A deep Q learning demonstration using Google Tensorflow
arjunchandra/dockerfiles
Compilation of Dockerfiles with automated builds enabled on the Docker Registry.
arjunchandra/DeepMind-Atari-Deep-Q-Learner
The original code from the DeepMind article + my tweaks
arjunchandra/deepframeworks
Evaluation of Deep Learning Frameworks
arjunchandra/veles
Distributed machine learning platform
arjunchandra/caffe
Caffe: a fast open framework for deep learning.
arjunchandra/Theano
Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.