Top Research Papers on Reinforcement Learning

DDPG reinforcement learning is proposed to generate and improve the walking motion of the quadruped robot, and the results show that the behaviour of the walking robot has been improved compared with the previous cases.

This work is one of the first to give tight regret guarantees for preference based RL problems with trajectory preferences, where the trajectory preferences are encoded by a generalized linear model of dimension $d.

This work proposes a novel set of mechanisms for grammar inference, RL-GRIT1, and shows that RL can be used to surpass the expressiveness of both classes, and offers a clear path to learning context-sensitive languages.

This article pioneer introducing the reinforcement learning (RL) model for mask optimization, which directly optimizes the preferred objective without leveraging a differentiable proxy, and outperforms state-of-the-art solutions.

This work introduces a two-level hierarchical framework, RL-GPT, comprising a slow agent and a fast agent, comprising a slow agent analyzes actions suitable for coding, while the fast agent executes coding tasks.

RL-ViGen is a novel Reinforcement Learning Benchmark for Visual Generalization, which contains diverse tasks and a wide spectrum of generalization types, thereby facilitating the derivation of more reliable conclusions and laying a foundation for the future creation of universal visual generalization RL agents suitable for real-world scenarios.

This paper focuses on the problem setting where both visual and tactile sensors provide pixel-level feedback for Visuotactile reinforcement learning agents, and investigates the challenges associated with multimodal learning and proposes several improvements to existing RL methods.

This paper proposes to represent a “fast” reinforcement learning algorithm as a recurrent neural network (RNN) and learn it from data, and shows that its performance on new MDPs is close to human-designed algorithms with optimality guarantees.

A new algorithm for distributed Reinforcement Learning (RL), a combination of the Alternating Direction Method of Multipliers (ADMM) and reinforcement learning that allows for integrating learned controllers as subsystems in generally convergent distributed control applications.

This document presents Open RL Benchmark, a set of fully tracked RL experiments, including not only the usual data such as episodic return, but also all algorithm-specific and system metrics, and is the first RL benchmark of its kind.

Throughout this training process, it is shown that the supernet gradually learns better cells, leading to alternative architectures which can be highly competitive against manually designed policies, but also verify previous design choices for RL policies.

This work casts several state-of-the-art offline RL and offline imitation learning algorithms as instances of dual RL approaches with shared structures, and proposes a new discriminator-free method ReCOIL that learns to imitate from arbitrary off-policy data to obtain near-expert performance.

SINDy-RL is introduced, a unifying framework for combining SINDy and DRL to create efficient, interpretable, and trustworthy representations of the dynamics model, reward function, and control policy that results in an interpretable control policy orders of magnitude smaller than a deep neural network policy.

This paper proposes a benchmark called RL Unplugged to evaluate and compare offline RL methods, a suite of benchmarks that will increase the reproducibility of experiments and make it possible to study challenging tasks with a limited computational budget, thus making RL research both more systematic and more accessible across the community.

A multiplier design optimization framework based on reinforcement learning is proposed, utilizing matrix and tensor representations for the compressor tree of a multiplier, enabling seamless integration of convolutional neural networks as the agent network.

Our life is getting filled by Internet of Things (IoT) devices. These devices often rely on closed or poorly documented protocols, with unknown formats and semantics. Learning how to interact with such devices in an autonomous manner is the key for interoperability and automatic verification of their capabilities. In this paper, we propose RL-IoT, a system that explores how to automatically interact with possibly unknown IoT devices. We leverage reinforcement learning (RL) to recover the semantics of protocol messages and to take control of the device to reach a given goal, while minimizing th...

This paper proposes to represent a "fast" reinforcement learning algorithm as a recurrent neural network (RNN) and learn it from data, encoded in the weights of the RNN, which are learned slowly through a general-purpose ("slow") RL algorithm.

The proposed EER-RL, an energy-efficient routing protocol based on reinforcement learning, allows devices to adapt to network changes, such as mobility and energy level, and improve routing decisions, and the results show that the proposed protocol performs better in terms of energy efficiency and network lifetime and scalability.

A novel method is introduced, RL-MLZerD, which builds multiple protein complexes using reinforcement learning (RL), and it emerged that the docking order of multi-chain complexes can be naturally predicted by examining preferred paths of episodes in the RL computation.

This work proposes Recovery RL, an algorithm which navigates this tradeoff by leveraging offline data to learn about constraint violating zones before policy learning and separating the goals of improving task performance and constraint satisfaction across two policies: a task policy that only optimizes the task reward and a recovery policy that guides the agent to safety when constraint violation is likely.

A novel Reinforcement Learning framework for the multimodal EMOtion recognition task (RL-EMO), which combines a Multi-modal Graph Convolution Network (MMGCN) module with a novel Reinforcement Learning (RL) module to model context at both the semantic and emotional levels respectively.

This work presents Robust Adversarial Model-Based Offline RL (RAMBO), a novel approach to model-based offline RL that addresses the problem as a two-player zero sum game against an adversarial environment model and demonstrates that it outperforms existing state-of-the-art baselines.

Experiments demonstrate that the model does not have to rely on a heuristic acquisition function like SMBO, but can learn which hyperparameters to test next based on the subsequent reduction in validation loss they will eventually lead to, and outperforms the state-of-the-art approaches for hyperparameter learning.

Results show that reinforcement learning algorithms embedded within the Evolutionary-Driven Reinforcement Learning approach significantly outperform the stand-alone versions of the same RL algorithms on OpenAI Gym control problems with rewardless states constrained by the same computational budget.

The experiments show that the proposed PR-RL method outperforms state-of-the-art methods in generating locally effective and interpretable high resolution relighting results for wild portrait images.

The new Deep Reinforcement Learning library RL-X provides a flexible and easy-to-extend codebase with self-contained single directory algorithms and its application to the RoboCup Soccer Simulation 3D League and classic DRL benchmarks is presented.

An RL-based approach in which the agent will select the access point with the highest SNR for establishing a communication link with the user is proposed, which helps in effective spectrum utilization and minimizing power wastage.

A deep reinforcement learning localization method for logo recognition (RL-LOGO) utilizes deep reinforcement learning to identify a logo region in images without annotations of the positions, thereby improving classification accuracy.

This work proposes a novel approach that uses reinforcement learning to generate a visual explanation for CNNs, and demonstrates that the proposed method outperforms the existing techniques, producing more accurate localization masks of regions of interest in the input images.

This work introduces FabricatioRL, an RL compatible, customizable and extensible benchmarking simulation framework that can interface with both traditional approaches and RL, and ensure that generic production setups can be covered, and experiments are reproducible.

The RL-CycleGAN, a new approach for simulation-to-real-world transfer for reinforcement learning, is obtained by incorporating the RL-scene consistency loss into unsupervised domain translation, which ensures that the translation operation is invariant with respect to the Q-values associated with the image.

The heading control of a KVLCC2 tanker in calm water and waves is investigated and the ship dynamics is represented using a 3DoF numerical model.

This letter proposes a novel hybrid architecture that reinforces a nominal controller with a robust policy learned using a model-free deep RL algorithm and employs an uncertainty-aware control mixer to preserve guaranteed stability of a nominal controllers while using the extended robust performance of the learned policy.

Muscle-actuated organisms are capable of learning an unparalleled diversity of dexterous movements despite their vast amount of muscles. Reinforcement learning (RL) on large musculoskeletal models, however, has not been able to show similar performance. We conjecture that ineffective exploration in large overactuated action spaces is a key problem. This is supported by the finding that common exploration noise strategies are inadequate in synthetic examples of overactuated systems. We identify differential extrinsic plasticity (DEP), a method from the domain of self-organization, as being able...

CFR-RL (Critical Flow Rerouting-Reinforcement Learning), a Reinforcement Learning-based scheme that learns a policy to select critical flows for each given traffic matrix automatically and reroutes these selected critical flows to balance link utilization of the network by formulating and solving a simple Linear Programming problem.

This paper proposes a benchmark called RL Unplugged to evaluate and compare offline RL methods, and proposes detailed evaluation protocols for each domain in RL Unplugged and provides an extensive analysis of supervised learning and offline RL methods using these protocols.

The experimental results demonstrate that the Reinforcement Learning agents are capable of achieving goals that are slightly relaxed both during the training and inference stages, and meticulously design hardware-efficient PQC architectures in the quantum model using a multi-objective evolutionary algorithm and develop a learning algorithm that is adaptable to Quafu.

Conformer‐RL is an open‐source Python package for applying deep reinforcement learning (RL) to the task of generating a diverse set of low‐energy conformations for a single molecule and contains modular class interfaces for RL environments and agents, allowing users to easily swap components with their own implementations.

This paper presents a novel RL-based approach for designing active controllers by introducing RL-Controller, a flexible and scalable simulation environment that includes attributes and functionalities that are defined to model active structural control mechanisms in detail.

The 7B model develops advanced reasoning skills-such as reflection, verification, and summarization-that are absent from the logic corpus after training on just 5K logic problems, and demonstrates generalization abilities to the challenging math benchmarks AIME and AMC.

This work argues the five fundamental properties of a sophisticated research codebase are modularity, reproducibility, many RL algorithms pre-implemented, speed and ease of running on different hardware/ integration with visualization packages.

This work takes the first step towards executing benchmark quantum reinforcement problems on real devices equipped with at most 136 qubits on the BAQIS Quafu quantum computing cloud and designs hardware-efficient PQC architectures in the quantum model using a multi-objective evolutionary algorithm and develops a learning algorithm that is adaptable to quantum devices.

This work proposes a novel and efficient reinforcement learning (RL) based task-aware prompt compression method that leverages existing Transformer encoder-based token classification model while guiding the learning process with task-specific reward signals using lightweight REINFORCE algorithm.

Applying a multi-step critic regularization method with a regularization coefficient of 1 yields the same policy as one-step RL, drawing a connection between these methods.

This letter proposes a reinforcement learning-based method for linguistic steganalysis that employs an agent (steganalyzer) to interact within an observation space, enabling adaptation to the characteristics of the transformed data and capturing Steganalysis features.

A two-dimensional simplified grid environment called "Flatland" that allows for faster experimentation and demonstrates that ML has potential in solving the VRSP on Flatland and identifies key topics that need further research.

This paper proposes goal distributions as a general and broadly applicable task representation suitable for contextual policies and develops an off-policy algorithm called distribution-conditioned reinforcement learning (DisCo RL) to efficiently learn these policies.

An architectural modification to Soar is described that gives a Soar agent the opportunity to learn statistical information about the past success of its actions and utilize this information when selecting an operator.

In this essay, the state-of-the-art RL is thoroughly reviewed in the literature and found in a wide range of industries, including smart grids, robots, computer vision, healthcare, gaming, transportation, finance, and engineering.

The Multi-Prior Regularized RL (MPR-RL) method is deployed directly on a real world Franka Panda arm, requiring only a set of demonstrated trajectories from similar, but crucially not identical, problem instances.