Neural Distillation as a State Representation Bottleneck in Reinforcement Learning Oct 5, 2022 reinforcement-learning Reinforcement Learning
— Unverified On Neural Consolidation for Transfer in Reinforcement Learning Oct 5, 2022 Deep Reinforcement Learning reinforcement-learning
— Unverified Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learning Oct 5, 2022 continuous-control Continuous Control
— Unverified Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees Oct 4, 2022 counterfactual Imitation Learning
— Unverified Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning Oct 4, 2022 Multi-agent Reinforcement Learning reinforcement-learning
Code Code Available DISCOVER: Deep identification of symbolically concise open-form PDEs via enhanced reinforcement-learning Oct 4, 2022 Deep Reinforcement Learning Form
Code Code Available Learning Dynamic Abstract Representations for Sample-Efficient Reinforcement Learning Oct 4, 2022 reinforcement-learning Reinforcement Learning
— Unverified Learning Perception-Aware Agile Flight in Cluttered Environments Oct 4, 2022 Imitation Learning Reinforcement Learning (RL)
— Unverified Using Deep Reinforcement Learning for mmWave Real-Time Scheduling Oct 4, 2022 Deep Reinforcement Learning reinforcement-learning
— Unverified Evaluating Disentanglement in Generative Models Without Knowledge of Latent Factors Oct 4, 2022 Disentanglement Fairness
— Unverified Handling Sparse Rewards in Reinforcement Learning Using Model Predictive Control Oct 4, 2022 Model Predictive Control reinforcement-learning
— Unverified Hyperbolic Deep Reinforcement Learning Oct 4, 2022 Decision Making Deep Reinforcement Learning
— Unverified Federated Reinforcement Learning for Real-Time Electric Vehicle Charging and Discharging Control Oct 4, 2022 reinforcement-learning Reinforcement Learning (RL)
— Unverified CostNet: An End-to-End Framework for Goal-Directed Reinforcement Learning Oct 3, 2022 reinforcement-learning Reinforcement Learning
— Unverified Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoders Oct 3, 2022 Deep Reinforcement Learning Q-Learning
— Unverified Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization Oct 3, 2022 Decision Making Policy Gradient Methods
Code Code Available CaiRL: A High-Performance Reinforcement Learning Environment Toolkit Oct 3, 2022 OpenAI Gym reinforcement-learning
Code Code Available Square-root regret bounds for continuous-time episodic Markov decision processes Oct 3, 2022 reinforcement-learning Reinforcement Learning (RL)
— Unverified Policy Gradient for Reinforcement Learning with General Utilities Oct 3, 2022 reinforcement-learning Reinforcement Learning
— Unverified MSRL: Distributed Reinforcement Learning with Dataflow Fragments Oct 3, 2022 CPU GPU
— Unverified Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient Oct 3, 2022 Decision Making Offline RL
— Unverified Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation Oct 3, 2022 reinforcement-learning Reinforcement Learning (RL)
— Unverified Mastering Spatial Graph Prediction of Road Networks Oct 3, 2022 Prediction Reinforcement Learning (RL)
— Unverified Latent State Marginalization as a Low-cost Approach for Improving Exploration Oct 3, 2022 continuous-control Continuous Control
Code Code Available Accelerate Reinforcement Learning with PID Controllers in the Pendulum Simulations Oct 3, 2022 reinforcement-learning Reinforcement Learning
Code Code Available Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation Oct 2, 2022 reinforcement-learning Reinforcement Learning
Code Code Available Policy Gradients for Probabilistic Constrained Reinforcement Learning Oct 2, 2022 reinforcement-learning Reinforcement Learning
— Unverified GFlowNets and variational inference Oct 2, 2022 Diversity Reinforcement Learning (RL)
Code Code Available EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model Oct 2, 2022 reinforcement-learning Reinforcement Learning (RL)
— Unverified Robust Bayesian optimization with reinforcement learned acquisition functions Oct 2, 2022 Bayesian Optimization reinforcement-learning
— Unverified Comparing BERT-based Reward Functions for Deep Reinforcement Learning in Machine Translation Oct 1, 2022 Deep Reinforcement Learning Machine Translation
— Unverified Can Data Diversity Enhance Learning Generalization? Oct 1, 2022 Diversity Domain Adaptation
— Unverified Parsing Natural Language into Propositional and First-Order Logic with Dual Reinforcement Learning Oct 1, 2022 Natural Language Inference reinforcement-learning
— Unverified Bayesian Q-learning With Imperfect Expert Demonstrations Oct 1, 2022 Atari Games Q-Learning
— Unverified Learning-Based Adaptive Optimal Control of Linear Time-Delay Systems: A Policy Iteration Approach Oct 1, 2022 Autonomous Driving Reinforcement Learning (RL)
— Unverified Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning Oct 1, 2022 Disentanglement Meta Reinforcement Learning
— Unverified Deep Intrinsically Motivated Exploration in Continuous Control Oct 1, 2022 continuous-control Continuous Control
Code Code Available Towards a Fully Autonomous UAV Controller for Moving Platform Detection and Landing Sep 30, 2022 Reinforcement Learning (RL)
— Unverified Efficiently Learning Small Policies for Locomotion and Manipulation Sep 30, 2022 reinforcement-learning Reinforcement Learning
— Unverified Efficient LSTM Training with Eligibility Traces Sep 30, 2022 Q-Learning Reinforcement Learning (RL)
— Unverified Improving Policy Learning via Language Dynamics Distillation Sep 30, 2022 NetHack Reinforcement Learning (RL)
Code Code Available ASPiRe:Adaptive Skill Priors for Reinforcement Learning Sep 30, 2022 reinforcement-learning Reinforcement Learning
— Unverified A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning Sep 30, 2022 reinforcement-learning Reinforcement Learning (RL)
— Unverified B2RL: An open-source Dataset for Building Batch Reinforcement Learning Sep 30, 2022 Management reinforcement-learning
Code Code Available Reward Shaping for User Satisfaction in a REINFORCE Recommender Sep 30, 2022 Imputation Reinforcement Learning (RL)
— Unverified Bounded Robustness in Reinforcement Learning via Lexicographic Objectives Sep 30, 2022 reinforcement-learning Reinforcement Learning
— Unverified RL-MD: A Novel Reinforcement Learning Approach for DNA Motif Discovery Sep 30, 2022 reinforcement-learning Reinforcement Learning (RL)
— Unverified Programmable Control of Ultrasound Swarmbots through Reinforcement Learning Sep 30, 2022 Diagnostic Navigate
— Unverified S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning Sep 30, 2022 Data Augmentation Image Generation
Code Code Available The Role of Time Delay in Sim2real Transfer of Reinforcement Learning for Cyber-Physical Systems Sep 30, 2022 Reinforcement Learning (RL)
— Unverified 