Share This Author
Dueling Network Architectures for Deep Reinforcement Learning
- Ziyun Wang, T. Schaul, Matteo Hessel, H. V. Hasselt, Marc Lanctot, N. D. Freitas
- Computer ScienceICML
- 20 November 2015
This paper presents a new neural network architecture for model-free reinforcement learning that leads to better policy evaluation in the presence of many similar-valued actions and enables the RL agent to outperform the state-of-the-art on the Atari 2600 domain.
Taking the Human Out of the Loop: A Review of Bayesian Optimization
- Bobak Shahriari, Kevin Swersky, Ziyun Wang, Ryan P. Adams, N. D. Freitas
- Computer ScienceProceedings of the IEEE
This review paper introduces Bayesian optimization, highlights some of its methodological aspects, and showcases a wide range of applications.
Grandmaster level in StarCraft II using multi-agent reinforcement learning
The agent, AlphaStar, is evaluated, which uses a multi-agent reinforcement learning algorithm and has reached Grandmaster level, ranking among the top 0.2% of human players for the real-time strategy game StarCraft II.
Sample Efficient Actor-Critic with Experience Replay
This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the…
Emergence of Locomotion Behaviours in Rich Environments
This paper explores how a rich environment can help to promote the learning of complex behavior, and finds that this encourages the emergence of robust behaviours that perform well across a suite of tasks.
Bayesian Optimization in a Billion Dimensions via Random Embeddings
- Ziyun Wang, M. Zoghi, F. Hutter, David Matheson, N. D. Freitas
- Computer ScienceJ. Artif. Intell. Res.
- 9 January 2013
Empirical results confirm that REMBO can effectively solve problems with billions of dimensions, provided the intrinsic dimensionality is low, and show thatREMBO achieves state-of-the-art performance in optimizing the 47 discrete parameters of a popular mixed integer linear programming solver.
Bayesian Optimization in High Dimensions via Random Embeddings
A novel random embedding idea is introduced to attack high-dimensional Bayesian optimization problems, and the resulting Random EMbedding Bayesian Optimization (REMBO) algorithm is very simple and applies to domains with both categorical and continuous variables.
Learning human behaviors from motion capture by adversarial imitation
Generative adversarial imitation learning is extended to enable training of generic neural network policies to produce humanlike movement patterns from limited demonstrations consisting only of partially observed state features, without access to actions, even when the demonstrations come from a body with different and unknown physical parameters.
Parallel Multiscale Autoregressive Density Estimation
This work proposes a parallelized PixelCNN that allows more efficient inference by modeling certain pixel groups as conditionally independent, achieving competitive density estimation and orders of magnitude speedup - O(log N) sampling instead of O(N) - enabling the practical generation of 512x512 images.
Playing hard exploration games by watching YouTube
- Y. Aytar, T. Pfaff, D. Budden, T. Paine, Ziyun Wang, N. D. Freitas
- Computer ScienceNeurIPS
- 29 May 2018
A two-stage method of one-shot imitation that allows an agent to convincingly exceed human-level performance on the infamously hard exploration games Montezuma's Revenge, Pitfall! and Private Eye for the first time, even if the agent is not presented with any environment rewards.