• Ray

  • Referenced in 7 articles [sw28740]
  • will continuously interact with the environment and learn from these interactions. These applications impose ... consider these requirements and present Ray---a distributed system to address them. Ray implements ... performance requirements, Ray employs a distributed scheduler and a distributed and fault-tolerant store ... existing specialized systems for several challenging reinforcement learning applications...
  • SURREAL

  • Referenced in 1 article [sw31156]
  • that runs state-of-the-art distributed reinforcement learning (RL) algorithms...
  • PyTorchRL

  • Referenced in 1 article [sw41243]
  • PyTorchRL: Modular and Distributed Reinforcement Learning in PyTorch. Deep reinforcement learning (RL) has proved successful ... modules. Additionally, PyTorchRL permits the definition of distributed training architectures with flexibility and independence...
  • IMPALA

  • Referenced in 10 articles [sw41064]
  • IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures. In this work ... collection of tasks using a single reinforcement learning agent with a single set of parameters ... training time. We have developed a new distributed agent IMPALA (Importance Weighted Actor-Learner Architecture ... achieve stable learning at high throughput by combining decoupled acting and learning with a novel...
  • RLgraph

  • Referenced in 2 articles [sw31155]
  • Computation Graphs for Deep Reinforcement Learning. Reinforcement learning (RL) tasks are challenging to implement, execute ... algorithmic instability, hyper-parameter sensitivity, and heterogeneous distributed communication patterns. We argue for the separation ... library for designing and executing reinforcement learning tasks in both static graph and define ... high performance across different deep learning frameworks and distributed backends...
  • ART 3

  • Referenced in 27 articles [sw08755]
  • implement parallel search of compressed or distributed pattern recognition codes in a neural network hierarchy ... functions well with either fast learning or slow learning, and can robustly cope with sequences ... memory representation of a pattern recognition code. Reinforcement feedback can modulate the search process...
  • Horizon

  • Referenced in 6 articles [sw31157]
  • Horizon, Facebook’s open source applied reinforcement learning (RL) platform. Horizon ... algorithms and includes data preprocessing, feature transformation, distributed training, counterfactual policy evaluation, optimized serving ... showcase and describe real examples where reinforcement learning models trained with Horizon significantly outperformed...
  • Catalyst.RL

  • Referenced in 3 articles [sw31154]
  • Distributed Framework for Reproducible RL Research. Despite the recent progress in deep reinforcement learning field ... library include large-scale asynchronous distributed training, easy-to-use configuration files with the complete...
  • DualDICE

  • Referenced in 1 article [sw40535]
  • Discounted Stationary Distribution Corrections. In many real-world reinforcement learning applications, access to the environment ... policy, accurate estimates of discounted stationary distribution ratios -- correction terms which quantify the likelihood that...
  • JRLF

  • Referenced in 1 article [sw14316]
  • testing reinforcement learning algorithms in a variety of environments. The current distribution contains implementation...
  • Seq2SQL

  • Referenced in 3 articles [sw27204]
  • Structured Queries from Natural Language using Reinforcement Learning. A significant amount of the world ... loop query execution over the database to learn a policy to generate unordered parts ... annotated examples of questions and SQL queries distributed across 24241 tables from Wikipedia. This dataset ... comparable datasets. By applying policy-based reinforcement learning with a query execution environment to WikiSQL...
  • RLDDE

  • Referenced in 3 articles [sw35866]
  • time delay. A novel method, called reinforcement learning-based dimension and delay estimator (RLDDE ... learn the selection policy of the dimension and delay under different distribution of the data...
  • SNAS

  • Referenced in 3 articles [sw42518]
  • optimization problem on parameters of a joint distribution for the search space in a cell ... gradient optimizes the same objective as reinforcement-learning-based NAS, but assigns credits to structural...
  • SAMBA

  • Referenced in 1 article [sw42123]
  • armed bandit is a reinforcement learning model where a learning agent repeatedly chooses an action ... stochastic outcome (reward) coming from an unknown distribution associated with the chosen arm. Bandits have...
  • LibPGRL

  • Referenced in 1 article [sw14310]
  • high-performance policy-gradient reinforcement learning library. Since the first version it has been extended ... iteration. It has been designed with large distributed RL systems in mind...
  • d3rlpy

  • Referenced in 1 article [sw40533]
  • d3rlpy, an open-sourced offline deep reinforcement learning (RL) library for Python. d3rlpy supports ... exporting policies for deployment, preprocessing and postprocessing, distributional Q-functions, multi-step learning...
  • MIMOSA

  • Referenced in 1 article [sw41883]
  • input molecule. Existing generative models and reinforcement learning approaches made initial success, but still face ... guess and sample molecules from the target distribution. MIMOSA first pretrains two property agnostic graph...
  • BaRC

  • Referenced in 3 articles [sw40037]
  • Learning. Model-free Reinforcement Learning (RL) offers an attractive approach to learn control policies ... amount of exploration required to obtain a learning signal from the initial state ... task, and expands the initial state distribution backwards in a dynamically-consistent manner once...
  • pymgrid

  • Referenced in 1 article [sw36564]
  • increasing infrastructure resiliency. Due to their distributed nature, microgrids are often idiosyncratic; as a result ... pymgrid is built to be a reinforcement learning (RL) platform, and includes the ability...
  • EAQR

  • Referenced in 1 article [sw27641]
  • design a multiagent reinforcement learning algorithm for cooperative tasks where multiple agents need to coordinate ... pushing, and the other is the distributed sensor network problem. Experimental results show that EAQR...