Information Gathering in Decentralized POMDPs by Policy Graph Improvement

26 Feb 20191 code implementation

Decentralized policies for information gathering are required when multiple autonomous agents are deployed to collect data about a phenomenon of interest without the ability to communicate.

DECISION MAKING

Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives

25 Jun 20191 code implementation

Reinforcement learning agents that operate in diverse and complex environments can benefit from the structured decomposition of their behavior.

HIERARCHICAL REINFORCEMENT LEARNING

On the Complexity of Exploration in Goal-Driven Navigation

16 Nov 20181 code implementation

Next, we propose to measure the complexity of each environment by constructing dependency graphs between the goals and analytically computing \emph{hitting times} of a random walk in the graph.

Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck

NeurIPS 2019 1 code implementation

We discuss those differences and propose modifications to existing regularization techniques in order to better adapt them to RL.

QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

ICML 2018 2 code implementations

At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting, where global state information is available and communication constraints are lifted.

MULTI-AGENT REINFORCEMENT LEARNING STARCRAFT STARCRAFT II

Long Text Generation via Adversarial Training with Leaked Information

24 Sep 20175 code implementations

Automatically generating coherent and semantically meaningful text has many applications in machine translation, dialogue systems, image captioning, etc.

TEXT GENERATION

Learning World Graphs to Accelerate Hierarchical Reinforcement Learning

1 Jul 20191 code implementation

We perform a thorough ablation study to evaluate our approach on a suite of challenging maze tasks, demonstrating significant advantages from the proposed framework over baselines that lack world graph knowledge in terms of performance and efficiency.

HIERARCHICAL REINFORCEMENT LEARNING

Transfer and Exploration via the Information Bottleneck

ICLR 2019 1 code implementation

In new environments, this model can then identify novel subgoals for further exploration, guiding the agent through a sequence of potential decision states and through new regions of the state space.

Recurrent Models of Visual Attention

NeurIPS 2014 10 code implementations

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels.

IMAGE CLASSIFICATION