arXiv research

MineRL Competition reduced reinforcement learning sample needs.

New framework promotes reproducible, domain-agnostic reinforcement learning algorithms.

Improved reinforcement learning in Minecraft with human demonstrations.

New algorithms prove self-play can be effective in competitive RL.

Competition aims to develop sample-efficient reinforcement learning methods.

In this study, we investigate the use of global information to speed up the learning process and increase the cumulative rewards of reinforcement learning (RL) in competition tasks. Within the actor-critic RL, we introduce multiple cooperative critics from two levels of the hierarchy and propose a reinforcement learnin…

A drone catches another agile drone using competitive reinforcement learning.

Framework for multi-agent RL with human feedback in a Snake game.

Agents learn to outperform in trading by using past and current prices.

Deep network learns Obstacle Tower challenge without human demonstrations.

This paper presents the first two editions of Visual Doom AI Competition, held in 2016 and 2017. The challenge was to create bots that compete in a multi-player deathmatch in a first-person shooter (FPS) game, Doom. The bots had to make their decisions based solely on visual information, i.e., a raw screen buffer. To p…

New method accelerates Pommerman training with imitation and reinforcement learning.

A framework for reinforcement learning tackles CVRP with competitive results.

Combining causality, control, and reinforcement learning for system control.

New algorithm improves self-play reinforcement learning for competitive games.

RL controls small soccer robots in a real league, beating human-designed policies.

New Soft Actor-Critic for discrete actions.

Agents trained with reinforcement learning deviate from Nash equilibrium in optimal execution game.

The General Video Game AI (GVGAI) competition and its associated software framework provides a way of benchmarking AI algorithms on a large number of games written in a domain-specific description language. While the competition has seen plenty of interest, it has so far focused on online planning, providing a forward …

Though deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples. As state-of-the-art reinforcement learning (RL) systems require an exponentially increasing number of samples, their development is restricted to a continually shrin…

The paper develops algorithms for competitive RL in partially observable MGs.

RS-DQN protects RL agents from adversarial attacks.

Paper tackles delays in multi-agent reinforcement learning, improving performance.

Deep learning has achieved remarkable successes in solving challenging reinforcement learning (RL) problems when dense reward function is provided. However, in sparse reward environment it still often suffers from the need to carefully shape reward function to guide policy optimization. This limits the applicability of…

Reinforcement learning agents that operate in diverse and complex environments can benefit from the structured decomposition of their behavior. Often, this is addressed in the context of hierarchical reinforcement learning, where the aim is to decompose a policy into lower-level primitives or options, and a higher-leve…

Reinforcement learning improves insurance claims reserving by learning from all claim trajectories.

New reinforcement learning bound improves generalization for sequential data.

A new imitation learning method uses random search for simple policies, outperforming complex models.

Novel framework for Bayesian reinforcement learning infers value function distributions.

In this paper, we explore using deep reinforcement learning for problems with multiple agents. Most existing methods for deep multi-agent reinforcement learning consider only a small number of agents. When the number of agents increases, the dimensionality of the input and control spaces increase as well, and these met…

Deep RL drone trained to compete against classical path planning in drone racing.

Learning to cooperate with friends and compete with foes is a key component of multi-agent reinforcement learning. Typically to do so, one requires access to either a model of or interaction with the other agent(s). Here we show how to learn effective strategies for cooperation and competition in an asymmetric informat…

To improve efficiency and reduce failures in autonomous vehicles, research has focused on developing robust and safe learning methods that take into account disturbances in the environment. Existing literature in robust reinforcement learning poses the learning problem as a two player game between the autonomous system…

Generative Adversarial Networks (GANs) have experienced a recent surge in popularity, performing competitively in a variety of tasks, especially in computer vision. However, GAN training has shown limited success in natural language processing. This is largely because sequences of text are discrete, and thus gradients …

Paper tackles RL for power grid topology optimization.

AlphaZeroBeta uses deep reinforcement learning for market-neutral portfolios, outperforming traditional methods.

This paper proposes GProp, a deep reinforcement learning algorithm for continuous policies with compatible function approximation. The algorithm is based on two innovations. Firstly, we present a temporal-difference based method for learning the gradient of the value-function. Secondly, we present the deviator-actor-cr…

We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural langu…

This paper proposes RDS to improve model diversity in data sampling.

Agents learn sophisticated tool use and coordination in hide-and-seek.

High-dimensional always-changing environments constitute a hard challenge for current reinforcement learning techniques. Artificial agents, nowadays, are often trained off-line in very static and controlled conditions in simulation such that training observations can be thought as sampled i.i.d. from the entire observa…

Meta-algorithm for efficient reinforcement learning from human preferences.

New machine learning pipeline solves dynamic vehicle routing problems efficiently.

We introduce a new algorithm for reinforcement learning called Maximum aposteriori Policy Optimisation (MPO) based on coordinate ascent on a relative entropy objective. We show that several existing methods can directly be related to our derivation. We develop two off-policy algorithms and demonstrate that they are com…

We consider a team of reinforcement learning agents that concurrently operate in a common environment, and we develop an approach to efficient coordinated exploration that is suitable for problems of practical scale. Our approach builds on seed sampling (Dimakopoulou and Van Roy, 2018) and randomized value function lea…

We propose and study a new model for reinforcement learning with rich observations, generalizing contextual bandits to sequential decision making. These models require an agent to take actions based on observations (features) with the goal of achieving long-term performance competitive with a large set of policies. To …

We formulate a general framework for competitive gradient-based learning that encompasses a wide breadth of multi-agent learning algorithms, and analyze the limiting behavior of competitive gradient-based learning algorithms using dynamical systems theory. For both general-sum and potential games, we characterize a non…

Unified framework for estimating reward functions in competitive games.