Data-Efficient Hierarchical Reinforcement Learning

NeurIPS 2018 5 code implementations

In this paper, we study how we can develop HRL algorithms that are general, in that they do not make onerous additional assumptions beyond standard RL algorithms, and efficient, in the sense that they can be used with modest numbers of interaction samples, making them suitable for real-world problems such as robotic control.

HIERARCHICAL REINFORCEMENT LEARNING

Data-Efficient Hierarchical Reinforcement Learning

NeurIPS 2018 1 code implementation

In this paper, we study how we can develop HRL algorithms that are general, in that they do not make onerous additional assumptions beyond standard RL algorithms, and efficient, in the sense that they can be used with modest numbers of interaction samples, making them suitable for real-world problems such as robotic control.

HIERARCHICAL REINFORCEMENT LEARNING

RLlib: Abstractions for Distributed Reinforcement Learning

ICML 2018 2 code implementations

Reinforcement learning (RL) algorithms involve the deep nesting of highly irregular computation patterns, each of which typically exhibits opportunities for distributed computation.

Deep Reinforcement Learning

15 Oct 20184 code implementations

We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources.

Implicit Quantile Networks for Distributional Reinforcement Learning

ICML 2018 11 code implementations

In this work, we build on recent advances in distributional reinforcement learning to give a generally applicable, flexible, and state-of-the-art distributional variant of DQN.

ATARI GAMES DISTRIBUTIONAL REINFORCEMENT LEARNING

Dopamine: A Research Framework for Deep Reinforcement Learning

14 Dec 20186 code implementations

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

Search on the Replay Buffer: Bridging Planning and Reinforcement Learning

NeurIPS 2019 1 code implementation

Our algorithm, search on the replay buffer (SoRB), enables agents to solve sparse reward tasks over hundreds of steps, and generalizes substantially better than standard RL algorithms.

StarCraft II: A New Challenge for Reinforcement Learning

16 Aug 201710 code implementations

Finally, we present initial baseline results for canonical deep reinforcement learning agents applied to the StarCraft II domain.

STARCRAFT STARCRAFT II

Interval timing in deep reinforcement learning agents

NeurIPS 2019 1 code implementation

The measurement of time is central to intelligent behavior.