2018-11
- Exploration by Random Network Distillation - arXiv
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding - arXiv
2018-05
- Stock Movement Prediction from Tweets and Historical Prices - paper
- Deterministic Policy Gradient Algorithms - paper
- Continuous control with deep reinforcement learning - arXiv
- Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments - arXiv
- Trust Region Policy Optimization - arXiv
- Sample Efficient Actor-Critic with Experience Replay - arXiv
- Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation - arXiv
2018-04
- Measuring the Intrinsic Dimension of Objective Landscapes - arXiv
- Prefrontal cortex as a meta-reinforcement learning system - BioArxiv
2018-03
- An Analysis of Neural Language Modeling at Multiple Scales - arXiv
- Averaging Weights Leads to Wider Optima and Better Generalization - arXiv
- Machine Theory of Mind - arXiv
- On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization - arXiv
- Diversity is All You Need: Learning Skills without a Reward Function - arXiv
2017-12
- Breaking the Softmax Bottleneck: A High-Rank RNN Language Model - arXiv
- Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm - arXiv
2017-11
- Proximal Policy Optimization Algorithms - arXiv
- Improving Factor-Based Quantitative Investing by Forecasting Company Fundamentals - arXiv
- TreeQN and ATreeC: Differentiable Tree Planning for Deep Reinforcement Learning - arXiv
- Non-Markovian Control with Gated End-to-End Memory Policy Networks - arXiv
2017-10
- Playing Atari with Deep Reinforcement Learning - arXiv - paper
- Deep Reinforcement Learning: An Overview - arXiv
- A Brief Survey of Deep Reinforcement Learning - arXiv
- A Deep Reinforcement Learning Chatbot - arXiv
2017-09
- StarSpace: Embed All The Things! - arXiv - Code
- Deep Neural Networks for YouTube Recommendations - Paper
- Improved Recurrent Neural Networks for Session-based Recommendations - arXiv
- Session-based Recommendations with Recurrent Neural Networks - arXiv
2017-08