- United Kingdom
Starred repositories
STUMPY is a powerful and scalable Python library for modern time series analysis
StellarGraph - Machine Learning on Graphs
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
Clean PyTorch implementations of imitation and reward learning algorithms
Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning
Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.
A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.
StarCraft II - pysc2 Deep Reinforcement Learning Examples
Inverse RL algorithms (APP, MaxEnt, GAIL, VAIL)
Implementations of Reinforcement Learning and Planning algorithms
DenseNet Implementation in Keras with ImageNet Pretrained Models
Code for Deep RL from Human Preferences [Christiano et al]. Plus a webapp for collecting human feedback
Reaver: Modular Deep Reinforcement Learning Framework. Focused on StarCraft II. Supports Gym, Atari, and MuJoCo.
Open-Source Distributed Reinforcement Learning Framework by Stanford Vision and Learning Lab
Code for the paper "When to Trust Your Model: Model-Based Policy Optimization"
Find best-response to a fixed policy in multi-agent RL
Hierarchy-based Image Embeddings for Semantic Image Retrieval
Random Network Distillation pytorch
Code for ICLR 2019 paper: Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks
Learning to Adapt in Dynamic, Real-World Environment through Meta-Reinforcement Learning
Multi-Agent Adversarial Inverse Reinforcement Learning, ICML 2019.
"Continuous Deep Q-Learning with Model-based Acceleration" in TensorFlow
Minimal Monte Carlo Policy Gradient (REINFORCE) Algorithm Implementation in Keras
This is a framework for the research on multi-agent reinforcement learning and the implementation of the experiments in the paper titled by ''Shapley Q-value: A Local Reward Approach to Solve Globa…
MetaGenRL, a novel meta reinforcement learning algorithm. Unlike prior work, MetaGenRL can generalize to new environments that are entirely different from those used for meta-training.