Results are presented on a new environment we call `Krazy World': a difficult high-dimensional gridworld which is designed to highlight the importance of correctly differentiating through sampling distributions in meta-reinforcement learning.
We consider the problem of exploration in meta reinforcement learning.
We propose a metalearning approach for learning gradient-based reinforcement learning (RL) algorithms.
Combining parameter noise with traditional RL methods allows to combine the best of both worlds.
In this work, we describe a surprising finding: a simple generalization of the classic count-based approach can reach near state-of-the-art performance on various high-dimensional and/or continuous deep RL benchmarks.
Ranked #1 on Atari Games on Atari 2600 Freeway
This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner.
Ranked #3 on Image Generation on Stanford Dogs
While there are methods with optimality guarantees in the setting of discrete state and action spaces, these methods cannot be applied in high-dimensional deep RL scenarios.
Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning.
Ranked #1 on Continuous Control on Inverted Pendulum
To improve prediction accuracy, this paper proposes: (i) Joint inference and learning by integration of back-propagation and loss-augmented inference in SSVM subgradient descent; (ii) Extending SSVM factors to neural networks that form highly nonlinear functions of input features.