• Publications
  • Influence
Dueling Network Architectures for Deep Reinforcement Learning
TLDR
We present a new neural network architecture for model-free reinforcement learning that can outperform the state-of-the-art on the Atari 2600 domain. Expand
Prioritized Experience Replay
TLDR
We use prioritized experience replay in Deep Q-Networks (DQN), a reinforcement learning algorithm that achieved human-level performance across Atari games. Expand
Rainbow: Combining Improvements in Deep Reinforcement Learning
TLDR
We show that several improvements to DQN can be successfully integrated into a single learning algorithm that achieves state-of-the-art performance. Expand
Learning to learn by gradient descent by gradient descent
TLDR
We show how the design of optimization algorithms can be cast as a learning problem, allowing the algorithm to learn to exploit structure in the problems of interest in an automatic way. Expand
Natural Evolution Strategies
TLDR
This paper presents natural evolution strategies (NES), a novel algorithm for performing real-valued dasiablack boxpsila function optimization: optimizing an unknown objective function where algorithm-selected function measurements constitute the only information accessible to the method. Expand
Unifying Count-Based Exploration and Intrinsic Motivation
TLDR
We use density models to measure uncertainty in non-tabular reinforcement learning, and propose a novel algorithm for deriving a pseudo-count from an arbitrary density model. Expand
Universal Value Function Approximators
TLDR
We introduce universal value function approximators (UVFAs) V (s, g; θ) that generalise not just over states s but also over goals g. Expand
Reinforcement Learning with Unsupervised Auxiliary Tasks
TLDR
In this paper, we introduce an agent that also maximises many other pseudo-reward functions simultaneously by reinforcement learning. Expand
Deep Q-learning From Demonstrations
TLDR
We present an algorithm, Deep Q-learning from Demonstrations (DQfD), that leverages small sets of demonstration data to massively accelerate the learning process even from relatively small amounts of demonstrationData and is able to automatically assess the necessary ratio of demonstrationdata while learning thanks to a prioritized replay mechanism. Expand
StarCraft II: A New Challenge for Reinforcement Learning
TLDR
This paper introduces SC2LE (StarCraft II Learning Environment), a reinforcement learning environment based on the StarCraft II game. Expand
...
1
2
3
4
5
...