Pinned Repositories
a3c-distributed_tensorflow
Distributed Tensorflow Implementation of Asynchronous Methods for Deep Reinforcement Learning
adv_attack_capsnet
Tensorflow Implementation of Adversarial Attack to Capsule Networks
bmaml
This repository contains implementations of the paper, Bayesian Model-Agnostic Meta-Learning.
bmaml_rl
This repository contains implementations of the paper, Bayesian Model-Agnostic Meta-Learning.
dreamer-torch
Pytorch version of Dreamer, which follows the original TF v2 codes.
Interaction-networks_tensorflow
Tensorflow Implementation of Interaction Networks for Learning about Objects, Relations and Physics
pathnet
Tensorflow Implementation of PathNet: Evolution Channels Gradient Descent in Super Neural Networks
programmable-agents_tensorflow
Tensorflow Implementation of Programmable Agents
SequentialData-GAN
Tensorflow Implementation of GAN modeling for sequential data
visual-interaction-networks_tensorflow
Tensorflow Implementation of Visual Interaction Networks
jsikyoon's Repositories
jsikyoon/dreamer-torch
Pytorch version of Dreamer, which follows the original TF v2 codes.
jsikyoon/bmaml_rl
This repository contains implementations of the paper, Bayesian Model-Agnostic Meta-Learning.
jsikyoon/V-MPO_torch
V-MPO torch version with DMLab30 and GTrXL
jsikyoon/OCRL
Object-Centric-Representation Library (OCRL): This repo is to explore OCR on various downstream tasks from supervised learning tasks to RL tasks.
jsikyoon/ddocker
jsikyoon/ASNP-RMR
This is an official Tensorflow implementation of the ASNP-RMR.
jsikyoon/my_ubuntu_settings
jsikyoon/rl-starter-files
RL starter files in order to immediatly train, visualize and evaluate an agent without writing any line of code
jsikyoon/scalable_agent
A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.
jsikyoon/torch-ac
Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO
jsikyoon/crafter
Benchmarking the Spectrum of Agent Capabilities
jsikyoon/dm_control
DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
jsikyoon/dreamer
Dream to Control: Learning Behaviors by Latent Imagination
jsikyoon/dreamer-1
Dream to Control: Learning Behaviors by Latent Imagination
jsikyoon/gym-minigrid
Minimalistic gridworld package for OpenAI Gym
jsikyoon/iris
Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.
jsikyoon/jsikyoon
profile
jsikyoon/lab
A customisable 3D platform for agent-based AI research
jsikyoon/lightning-bolts
Toolbox of models, callbacks, and datasets for AI/ML researchers.
jsikyoon/Miniworld
Simple and easily configurable 3D FPS-game-like environments for reinforcement learning
jsikyoon/pycolab
A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning agents!
jsikyoon/pytorch-a2c-ppo-acktr-gail
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
jsikyoon/pytorch-ntm
Neural Turing Machines (NTM) - PyTorch Implementation
jsikyoon/Recall2Imagine
To investigate R2I framework on my side
jsikyoon/seed_rl
SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.
jsikyoon/snp
Sequential Neural Processes
jsikyoon/SPACE
Official PyTorch implementation of "SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition"
jsikyoon/spriteworld
Spriteworld: a flexible, configurable python-based reinforcement learning environment
jsikyoon/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
jsikyoon/tkipf.github.io