Reading Group

Latest papers can be found here.

The Predictron: End-To-End Learning and Planning

#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning

Trust Region Policy Optimization (TRPO)

Reinforcement Learning with Unsupervised Auxiliary Tasks (UNREAL)

Learning to reinforcement learn

Deep Reinforcement Learning for Visual Object Tracking in Videos

Learning to Act by Predicting the Future

Neural Map: Structured Memory for Deep Reinforcement Learning

Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation

Hybrid computing using a neural network with dynamic external memory

Evolution Strategies as a Scalable Alternative to Reinforcement Learning

Data-efficient Deep Reinforcement Learning for Dexterous Manipulation

Learning from Demonstrations for Real World Reinforcement Learning

DeepLoco: Dynamic Locomotion Skills Using Hierarchical Deep Reinforcement Learning 

Automatic Goal Generation for Reinforcement Learning Agents

Hindsight Experience Replay

Emergence of Locomotion Behaviours in Rich Environments

Proximal Policy Optimization Algorithms

Reverse Curriculum Generation for Reinforcement Learning

The Intentional Unintentional Agent: Learning to Solve Many Continuous Control Tasks Simultaneously

Learning model-based planning from scratch

DARLA: Improving Zero-Shot Transfer in Reinforcement Learning

The Uncertainty Bellman Equation and Exploration

Distral: Robust Multitask Reinforcement Learning

Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards

Emergent Complexity via Multi-agent Competition

Rainbow: Combining Improvements in Deep Reinforcement Learning

Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning

Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments

Imagination-Augmented Agents for Deep Reinforcement Learning

Divide-and-Conquer Reinforcement Learning

Action Branching Architectures for Deep Reinforcement Learning

Time Limits in Reinfocement Learning

Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning

Mastering the game of Go without human knowledge

Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations

IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

Learning an Embedding Space for Transferable Robot Skills

Zero-Shot Visual Imitation

Motion Planning Networks

Counterfactual Multi-Agent Policy Gradients

Learning to Adapt: Meta-Learning for Model-Based Control

Hierarchical Imitation and Reinforcement Learning

SOLAR: Deep Structured Latent Representations for Model-Based Reinforcement Learning

Model-Based Reinforcement Learning via Meta-Policy Optimization