arXiv research

VASE uses Bayesian neural networks to improve exploration in sparse reward environments.

New approach uses unlabeled prior data to accelerate exploration in sparse reward tasks.

A new approach for deep exploration in sparse reward reinforcement learning.

New method combines curiosity and hindsight for stacking blocks.

R3L uses planning algorithms to efficiently explore sparse reward environments.

The paper introduces a method for multi-agent reinforcement learning to coordinate exploration.

BeBold improves exploration in sparse-reward tasks by regulating visitation counts.

ETGL-DDPG improves DDPG for sparse reward control with new exploration and replay techniques.

Project explores reinforcement learning solutions for sparse reward environments.

New bounds for high-dimensional sparse linear bandits, balancing information and regret.

We propose Deep Q-Networks (DQN) with model-based exploration, an algorithm combining both model-free and model-based approaches that explores better and learns environments with sparse rewards more efficiently. DQN is a general-purpose, model-free algorithm and has been proven to perform well in a variety of tasks inc…

Reinforcement learning agents need exploratory behaviors to escape from local optima. These behaviors may include both immediate dithering perturbation and temporally consistent exploration. To achieve these, a stochastic policy model that is inherently consistent through a period of time is in desire, especially for t…

This work learns latent representations to speed up exploration in complex environments.

HyperX uses reward bonuses to enable efficient exploration in meta-learning.

Sparse reward is one of the biggest challenges in reinforcement learning (RL). In this paper, we propose a novel method called Generative Exploration and Exploitation (GENE) to overcome sparse reward. GENE automatically generates start states to encourage the agent to explore the environment and to exploit received rew…

This paper tackles hard exploration in the game Pommerman, improving RL learning.

Action guidance helps agents learn true objectives in games with sparse rewards.

Entropy regularization improves sparse model discovery in federated learning.

Sparse coding, which represents a data point as a sparse reconstruction code with regard to a dictionary, has been a popular data representation method. Meanwhile, in database retrieval problems, learning the ranking scores from data points plays an important role. Up to now, these two problems have always been conside…

This paper proposes an exploration method for deep reinforcement learning based on parameter space noise. Recent studies have experimentally shown that parameter space noise results in better exploration than the commonly used action space noise. Previous methods devised a way to update the diagonal covariance matrix o…

This work uses model uncertainty for efficient exploration in sparse reward environments.

A new HRL algorithm learns and exploits multiple subgoals for faster exploration.

New RL agent learns sparse rewards efficiently.

MADE improves exploration in RL by maximizing deviation from explored regions.

A method for self-supervised representation learning in partially observable environments.

We introduce Graph-Sparse Logistic Regression, a new algorithm for classification for the case in which the support should be sparse but connected on a graph. We val- idate this algorithm against synthetic data and benchmark it against L1-regularized Logistic Regression. We then explore our technique in the bioinformat…

Sparse RSP routing improves graph exploration and classification.

This paper explores efficient neural networks by identifying sparse structures.

SAC-NF improves RL exploration by using normalizing flows to discover policies faster.

Exploration in sparse reward reinforcement learning remains an open challenge. Many state-of-the-art methods use intrinsic motivation to complement the sparse extrinsic reward signal, giving the agent more opportunities to receive feedback during exploration. Commonly these signals are added as bonus rewards, which res…

IDS improves sparse linear bandits by balancing information and regret.

The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model and its uncertainties. However, the current algorithms lack an effec…

This paper explores loss landscapes of sparse neural networks, finding unique characteristics compared to dense networks.

This research enhances exploration in DDPG using latent trajectory optimization.

SUPE combines unlabeled data with RL to efficiently explore tasks.

Modern deep neural networks are typically highly overparameterized. Pruning techniques are able to remove a significant fraction of network parameters with little loss in accuracy. Recently, techniques based on dynamic reallocation of non-zero parameters have emerged, allowing direct training of sparse networks without…

The sizes of deep neural networks (DNNs) are rapidly outgrowing the capacity of hardware to store and train them. Research over the past few decades has explored the prospect of sparsifying DNNs before, during, and after training by pruning edges from the underlying topology. The resulting neural network is known as a …

New methods solve sparse estimation robustly, even with outliers.

New algorithms approximate Rashomon set for sparse models, aiding expert interaction.

Study improves materials discovery for high-entropy alloys using sparse linear models.

Paper explores variable skipping to speed up range density estimation.

Paper explores robustness of CCS model for matrix completion.

In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the agent to explore its environment and learn skills that might be useful later in its life. We formulate curiosity as the error in an agen…

Paper identifies sparse structures and communities in heterogeneous graphical models.

We investigate sparse representations for control in reinforcement learning. While these representations are widely used in computer vision, their prevalence in reinforcement learning is limited to sparse coding where extracting representations for new data can be computationally intensive. Here, we begin by demonstrat…

A method to train multi-agent reinforcement learning models without intrinsic rewards.

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…

Campfire simplifies sparse training for CNNs, achieving high accuracy with minimal pruning.