{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/reinforcement-learning-2/papers/75","list_of":"/task/reinforcement-learning-2","task":"reinforcement-learning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":75,"pages_in_order":135,"rows_per_page":100,"rows":[7401,7500],"of":13427,"counts":{"archive_papers_tagged":13427,"with_a_code_link":4119,"where_syntology_ran_a_sample":1165,"not_listed_spam_title":0,"listed":13427,"listed_where_code_ran":1165,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":973,"every_run_a_failure_of_syntologys_instrument":192,"listed_with_a_run_with_no_instrument_failure":973,"listed_every_run_a_failure_of_syntologys_instrument":192,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/reinforcement-learning-2","prev":"/task/reinforcement-learning-2/papers/74","next":"/task/reinforcement-learning-2/papers/76","papers":[{"url":null,"slug":"the-impact-of-task-underspecification-in","title":"The Impact of Task Underspecification in Evaluating Deep Reinforcement Learning","date":"2022-10-16","arxiv_id":"2210.08607","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-an-interpretable-hierarchical-agent","title":"Towards an Interpretable Hierarchical Agent Framework using Semantic Goals","date":"2022-10-16","arxiv_id":"2210.08412","repositories_listed":0,"syntology":null},{"url":null,"slug":"dyfen-agent-based-fee-setting-in-payment","title":"DyFEn: Agent-Based Fee Setting in Payment Channel Networks","date":"2022-10-15","arxiv_id":"2210.08197","repositories_listed":0,"syntology":null},{"url":null,"slug":"near-optimal-regret-bounds-for-multi-batch","title":"Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning","date":"2022-10-15","arxiv_id":"2210.08238","repositories_listed":0,"syntology":null},{"url":null,"slug":"pi-qt-opt-predictive-information-improves","title":"PI-QT-Opt: Predictive Information Improves Multi-Task Robotic Reinforcement Learning at Scale","date":"2022-10-15","arxiv_id":"2210.08217","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-connectx","title":"Reinforcement Learning for ConnectX","date":"2022-10-15","arxiv_id":"2210.08263","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-approach-to-3","title":"A Reinforcement Learning Approach to Estimating Long-term Treatment Effects","date":"2022-10-14","arxiv_id":"2210.07536","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-scalable-finite-difference-method-for-deep","title":"A Scalable Finite Difference Method for Deep Reinforcement Learning","date":"2022-10-14","arxiv_id":"2210.07487","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptable-claim-rewriting-with-offline","title":"Query Rewriting for Effective Misinformation Discovery","date":"2022-10-14","arxiv_id":"2210.07467","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-patch-foraging-in-deep-reinforcement","title":"Adaptive patch foraging in deep reinforcement learning agents","date":"2022-10-14","arxiv_id":"2210.08085","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-trainer-interactive-reinforcement","title":"Multi-trainer Interactive Reinforcement Learning System","date":"2022-10-14","arxiv_id":"2210.08050","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-preference-learning-for-storytelling","title":"Robust Preference Learning for Storytelling via Contrastive Reinforcement Learning","date":"2022-10-14","arxiv_id":"2210.07792","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-concise-introduction-to-reinforcement","title":"A Concise Introduction to Reinforcement Learning in Robotics","date":"2022-10-13","arxiv_id":"2210.07397","repositories_listed":0,"syntology":null},{"url":null,"slug":"causality-driven-hierarchical-structure","title":"Causality-driven Hierarchical Structure Discovery for Reinforcement Learning","date":"2022-10-13","arxiv_id":"2210.06964","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-circuit-implementation-for-coined","title":"Efficient circuit implementation for coined quantum walks on binary trees and application to reinforcement learning","date":"2022-10-13","arxiv_id":"2210.06784","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-category-aware-reinforcement-learning","title":"Object-Category Aware Reinforcement Learning","date":"2022-10-13","arxiv_id":"2210.07802","repositories_listed":0,"syntology":null},{"url":null,"slug":"observed-adversaries-in-deep-reinforcement","title":"Observed Adversaries in Deep Reinforcement Learning","date":"2022-10-13","arxiv_id":"2210.06787","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-control-of-material-micro-structures","title":"Optimal Control of Material Micro-Structures","date":"2022-10-13","arxiv_id":"2210.06734","repositories_listed":0,"syntology":null},{"url":null,"slug":"output-feedback-adaptive-optimal-control-of","title":"Output Feedback Adaptive Optimal Control of Affine Nonlinear systems with a Linear Measurement Model","date":"2022-10-13","arxiv_id":"2210.06637","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalized-federated-hypernetworks-for","title":"Personalized Federated Hypernetworks for Privacy Preservation in Multi-Task Reinforcement Learning","date":"2022-10-13","arxiv_id":"2210.06820","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-unbiased-policy","title":"Reinforcement Learning with Unbiased Policy Evaluation and Linear Function Approximation","date":"2022-10-13","arxiv_id":"2210.07338","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-multi-agent-reinforcement-learning-2","title":"Towards Multi-Agent Reinforcement Learning driven Over-The-Counter Market Simulations","date":"2022-10-13","arxiv_id":"2210.07184","repositories_listed":0,"syntology":null},{"url":null,"slug":"dqlap-deep-q-learning-recommender-algorithm","title":"DQLAP: Deep Q-Learning Recommender Algorithm with Update Policy for a Real Steam Turbine System","date":"2022-10-12","arxiv_id":"2210.06399","repositories_listed":0,"syntology":null},{"url":null,"slug":"explaining-online-reinforcement-learning","title":"Explaining Online Reinforcement Learning Decisions of Self-Adaptive Systems","date":"2022-10-12","arxiv_id":"2210.05931","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-world-offline-reinforcement-learning","title":"Real World Offline Reinforcement Learning with Realistic Data Source","date":"2022-10-12","arxiv_id":"2210.06479","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-automated","title":"Reinforcement Learning with Automated Auxiliary Loss Search","date":"2022-10-12","arxiv_id":"2210.06041","repositories_listed":0,"syntology":null},{"url":null,"slug":"smooth-trajectory-collision-avoidance-through","title":"Smooth Trajectory Collision Avoidance through Deep Reinforcement Learning","date":"2022-10-12","arxiv_id":"2210.06377","repositories_listed":0,"syntology":null},{"url":null,"slug":"broad-persistent-advice-for-interactive","title":"Broad-persistent Advice for Interactive Reinforcement Learning Scenarios","date":"2022-10-11","arxiv_id":"2210.05187","repositories_listed":0,"syntology":null},{"url":null,"slug":"edge-cloud-cooperation-for-dnn-inference-via","title":"Edge-Cloud Cooperation for DNN Inference via Reinforcement Learning and Supervised Learning","date":"2022-10-11","arxiv_id":"2210.05182","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-user-reinforcement-learning-with-low","title":"Multi-User Reinforcement Learning with Low Rank Rewards","date":"2022-10-11","arxiv_id":"2210.05355","repositories_listed":0,"syntology":null},{"url":null,"slug":"regret-bounds-for-risk-sensitive","title":"Regret Bounds for Risk-Sensitive Reinforcement Learning","date":"2022-10-11","arxiv_id":"2210.05650","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-role-of-exploration-for-task-transfer-in","title":"The Role of Exploration for Task Transfer in Reinforcement Learning","date":"2022-10-11","arxiv_id":"2210.06168","repositories_listed":0,"syntology":null},{"url":null,"slug":"creating-a-dynamic-quadrupedal-robotic","title":"Creating a Dynamic Quadrupedal Robotic Goalkeeper with Reinforcement Learning","date":"2022-10-10","arxiv_id":"2210.04435","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-n-step-surrogate-stage-reward-to-reduce","title":"Long N-step Surrogate Stage Reward to Reduce Variances of Deep Reinforcement Learning in Complex Problems","date":"2022-10-10","arxiv_id":"2210.04820","repositories_listed":0,"syntology":null},{"url":null,"slug":"simulating-coverage-path-planning-with-roomba","title":"Simulating Coverage Path Planning with Roomba","date":"2022-10-10","arxiv_id":"2210.04988","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-theoretical-foundation-of-policy","title":"Towards a Theoretical Foundation of Policy Optimization for Learning Control Policies","date":"2022-10-10","arxiv_id":"2210.04810","repositories_listed":0,"syntology":null},{"url":null,"slug":"equivalency-of-optimality-criteria-of-markov","title":"Equivalence of Optimality Criteria for Markov Decision Process and Model Predictive Control","date":"2022-10-09","arxiv_id":"2210.04302","repositories_listed":0,"syntology":null},{"url":"/paper/state-advantage-weighting-for-offline-rl","slug":"state-advantage-weighting-for-offline-rl","title":"State Advantage Weighting for Offline RL","date":"2022-10-09","arxiv_id":"2210.04251","repositories_listed":0,"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 5 unverified","sample_list":"/paper/state-advantage-weighting-for-offline-rl#ran","syntology_url":"https://syntology.ai/paper/2210.04251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.04251"}},"official":null}},{"url":null,"slug":"the-role-of-coverage-in-online-reinforcement","title":"The Role of Coverage in Online Reinforcement Learning","date":"2022-10-09","arxiv_id":"2210.04157","repositories_listed":0,"syntology":null},{"url":null,"slug":"advice-conformance-verification-by","title":"Advice Conformance Verification by Reinforcement Learning agents for Human-in-the-Loop","date":"2022-10-07","arxiv_id":"2210.03455","repositories_listed":0,"syntology":null},{"url":null,"slug":"algorithmic-trading-using-continuous-action","title":"Algorithmic Trading Using Continuous Action Space Deep Reinforcement Learning","date":"2022-10-07","arxiv_id":"2210.03469","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-deep-covering-option-discovery","title":"Multi-agent Deep Covering Skill Discovery","date":"2022-10-07","arxiv_id":"2210.03269","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-approach-for-multi","title":"Reinforcement Learning Approach for Multi-Agent Flexible Scheduling Problems","date":"2022-10-07","arxiv_id":"2210.03674","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-inventory-management","title":"Deep Inventory Management","date":"2022-10-06","arxiv_id":"2210.03137","repositories_listed":0,"syntology":null},{"url":null,"slug":"digital-human-interactive-recommendation","title":"Digital Human Interactive Recommendation Decision-Making Based on Reinforcement Learning","date":"2022-10-06","arxiv_id":"2210.10638","repositories_listed":0,"syntology":null},{"url":"/paper/distributionally-adaptive-meta-reinforcement","slug":"distributionally-adaptive-meta-reinforcement","title":"Distributionally Adaptive Meta Reinforcement Learning","date":"2022-10-06","arxiv_id":"2210.03104","repositories_listed":0,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/distributionally-adaptive-meta-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2210.03104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03104"}},"official":null}},{"url":null,"slug":"learning-algorithms-for-intelligent-agents","title":"Learning Algorithms for Intelligent Agents and Mechanisms","date":"2022-10-06","arxiv_id":"2210.02654","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-thrust-orbital-transfer-using-dynamics","title":"Low-Thrust Orbital Transfer using Dynamics-Agnostic Reinforcement Learning","date":"2022-10-06","arxiv_id":"2211.08272","repositories_listed":0,"syntology":null},{"url":null,"slug":"lyapunov-function-consistent-adaptive-network","title":"Lyapunov Function Consistent Adaptive Network Signal Control with Back Pressure and Reinforcement Learning","date":"2022-10-06","arxiv_id":"2210.02612","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-reinforcement-learning-for-optimal","title":"Meta Reinforcement Learning for Optimal Design of Legged Robots","date":"2022-10-06","arxiv_id":"2210.02750","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-large-action-1","title":"Reinforcement Learning with Large Action Spaces for Neural Machine Translation","date":"2022-10-06","arxiv_id":"2210.03053","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-entropy-maximizing-td3-based","title":"A Novel Entropy-Maximizing TD3-based Reinforcement Learning for Automatic PID Tuning","date":"2022-10-05","arxiv_id":"2210.02381","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-distillation-as-a-state-representation","title":"Neural Distillation as a State Representation Bottleneck in Reinforcement Learning","date":"2022-10-05","arxiv_id":"2210.02224","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-neural-consolidation-for-transfer-in","title":"On Neural Consolidation for Transfer in Reinforcement Learning","date":"2022-10-05","arxiv_id":"2210.02240","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-the-agent-improving-sample-efficiency","title":"Query The Agent: Improving sample efficiency through epistemic uncertainty estimation","date":"2022-10-05","arxiv_id":"2210.02585","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-scheduling","title":"Using Deep Reinforcement Learning for mmWave Real-Time Scheduling","date":"2022-10-04","arxiv_id":"2210.01423","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-reinforcement-learning-for-real","title":"Federated Reinforcement Learning for Real-Time Electric Vehicle Charging and Discharging Control","date":"2022-10-04","arxiv_id":"2210.01452","repositories_listed":0,"syntology":null},{"url":null,"slug":"handling-sparse-rewards-in-reinforcement","title":"Handling Sparse Rewards in Reinforcement Learning Using Model Predictive Control","date":"2022-10-04","arxiv_id":"2210.01525","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperbolic-deep-reinforcement-learning","title":"Hyperbolic Deep Reinforcement Learning","date":"2022-10-04","arxiv_id":"2210.01542","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-dynamic-abstract-representations-for","title":"Learning Dynamic Abstract Representations for Sample-Efficient Reinforcement Learning","date":"2022-10-04","arxiv_id":"2210.01955","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximum-likelihood-inverse-reinforcement","title":"Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees","date":"2022-10-04","arxiv_id":"2210.01808","repositories_listed":0,"syntology":null},{"url":null,"slug":"costnet-an-end-to-end-framework-for-goal","title":"CostNet: An End-to-End Framework for Goal-Directed Reinforcement Learning","date":"2022-10-03","arxiv_id":"2210.01805","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-option-discovery-using-deep-q","title":"Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoders","date":"2022-10-03","arxiv_id":"2210.01231","repositories_listed":0,"syntology":null},{"url":null,"slug":"msrl-distributed-reinforcement-learning-with","title":"MSRL: Distributed Reinforcement Learning with Dataflow Fragments","date":"2022-10-03","arxiv_id":"2210.00882","repositories_listed":0,"syntology":null},{"url":null,"slug":"near-optimal-deployment-efficiency-in-reward","title":"Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation","date":"2022-10-03","arxiv_id":"2210.00701","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-reinforcement-learning-with-5","title":"Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient","date":"2022-10-03","arxiv_id":"2210.00750","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-gradient-for-reinforcement-learning","title":"Policy Gradient for Reinforcement Learning with General Utilities","date":"2022-10-03","arxiv_id":"2210.00991","repositories_listed":0,"syntology":null},{"url":null,"slug":"square-root-regret-bounds-for-continuous-time","title":"Square-root regret bounds for continuous-time episodic Markov decision processes","date":"2022-10-03","arxiv_id":"2210.00832","repositories_listed":0,"syntology":null},{"url":null,"slug":"euclid-towards-efficient-unsupervised","title":"EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model","date":"2022-10-02","arxiv_id":"2210.00498","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-gradients-for-probabilistic","title":"Policy Gradients for Probabilistic Constrained Reinforcement Learning","date":"2022-10-02","arxiv_id":"2210.00596","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-bayesian-optimization-with","title":"Robust Bayesian optimization with reinforcement learned acquisition functions","date":"2022-10-02","arxiv_id":"2210.00476","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-q-learning-with-imperfect-expert","title":"Bayesian Q-learning With Imperfect Expert Demonstrations","date":"2022-10-01","arxiv_id":"2210.01800","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-bert-based-reward-functions-for","title":"Comparing BERT-based Reward Functions for Deep Reinforcement Learning in Machine Translation","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parsing-natural-language-into-propositional-1","title":"Parsing Natural Language into Propositional and First-Order Logic with Dual Reinforcement Learning","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-policy-transfer-with-disentangled-1","title":"Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning","date":"2022-10-01","arxiv_id":"2210.00350","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-general-framework-for-sample-efficient","title":"A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning","date":"2022-09-30","arxiv_id":"2209.15634","repositories_listed":0,"syntology":null},{"url":null,"slug":"aspire-adaptive-skill-priors-for","title":"ASPiRe:Adaptive Skill Priors for Reinforcement Learning","date":"2022-09-30","arxiv_id":"2209.15205","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficiently-learning-small-policies-for","title":"Efficiently Learning Small Policies for Locomotion and Manipulation","date":"2022-09-30","arxiv_id":"2210.00140","repositories_listed":0,"syntology":null},{"url":null,"slug":"observational-robustness-and-invariances-in","title":"Bounded Robustness in Reinforcement Learning via Lexicographic Objectives","date":"2022-09-30","arxiv_id":"2209.15320","repositories_listed":0,"syntology":null},{"url":null,"slug":"programmable-control-of-ultrasound-swarmbots","title":"Programmable Control of Ultrasound Swarmbots through Reinforcement Learning","date":"2022-09-30","arxiv_id":"2209.15393","repositories_listed":0,"syntology":null},{"url":null,"slug":"rl-md-a-novel-reinforcement-learning-approach","title":"RL-MD: A Novel Reinforcement Learning Approach for DNA Motif Discovery","date":"2022-09-30","arxiv_id":"2209.15181","repositories_listed":0,"syntology":null},{"url":null,"slug":"blessing-from-experts-super-reinforcement","title":"Blessing from Human-AI Interaction: Super Reinforcement Learning in Confounded Environments","date":"2022-09-29","arxiv_id":"2209.15448","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-unsupervised-learning-of-world","title":"Contrastive Unsupervised Learning of World Model with Invariant Causal Features","date":"2022-09-29","arxiv_id":"2209.14932","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-training-of-deep-ensemble","title":"Ensemble Reinforcement Learning in Continuous Spaces -- A Hierarchical Multi-Step Approach for Policy Training","date":"2022-09-29","arxiv_id":"2209.14488","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-does-value-distribution-in-distributional","title":"How Does Return Distribution in Distributional Reinforcement Learning Help Optimization?","date":"2022-09-29","arxiv_id":"2209.14513","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-parsimonious-dynamics-for","title":"Learning Parsimonious Dynamics for Generalization in Reinforcement Learning","date":"2022-09-29","arxiv_id":"2209.14781","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-weighted-q-ensembles-for-reduced","title":"Online Weighted Q-Ensembles for Reduced Hyperparameter Tuning in Reinforcement Learning","date":"2022-09-29","arxiv_id":"2209.15078","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-algorithms-an-overview","title":"Reinforcement Learning Algorithms: An Overview and Classification","date":"2022-09-29","arxiv_id":"2209.14940","repositories_listed":0,"syntology":null},{"url":null,"slug":"argumentative-reward-learning-reasoning-about","title":"Argumentative Reward Learning: Reasoning About Human Preferences","date":"2022-09-28","arxiv_id":"2209.14010","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangling-transfer-in-continual","title":"Disentangling Transfer in Continual Reinforcement Learning","date":"2022-09-28","arxiv_id":"2209.13900","repositories_listed":0,"syntology":null},{"url":null,"slug":"fire-a-failure-adaptive-reinforcement","title":"FIRE: A Failure-Adaptive Reinforcement Learning Framework for Edge Computing Migrations","date":"2022-09-28","arxiv_id":"2209.14399","repositories_listed":0,"syntology":null},{"url":null,"slug":"guiding-safe-exploration-with-weakest","title":"Guiding Safe Exploration with Weakest Preconditions","date":"2022-09-28","arxiv_id":"2209.14148","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-generalization-of-deep-reinforcement","title":"Generalization in Deep Reinforcement Learning for Robotic Navigation by Reward Shaping","date":"2022-09-28","arxiv_id":"2209.14271","repositories_listed":0,"syntology":null},{"url":null,"slug":"predictive-crypto-asset-automated-market","title":"Predictive Crypto-Asset Automated Market Making Architecture for Decentralized Finance using Deep Reinforcement Learning","date":"2022-09-28","arxiv_id":"2211.01346","repositories_listed":0,"syntology":null},{"url":null,"slug":"dce-offline-reinforcement-learning-with","title":"DCE: Offline Reinforcement Learning With Double Conservative Estimates","date":"2022-09-27","arxiv_id":"2209.13132","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-non-exponential","title":"Reinforcement Learning with Non-Exponential Discounting","date":"2022-09-27","arxiv_id":"2209.13413","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-reinforcement-learning-of-dynamic-high","title":"Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction","date":"2022-09-27","arxiv_id":"2209.13308","repositories_listed":0,"syntology":null},{"url":null,"slug":"deft-diverse-ensembles-for-fast-transfer-in","title":"DEFT: Diverse Ensembles for Fast Transfer in Reinforcement Learning","date":"2022-09-26","arxiv_id":"2209.12412","repositories_listed":0,"syntology":null},{"url":null,"slug":"delayed-geometric-discounts-an-alternative-1","title":"Delayed Geometric Discounts: An Alternative Criterion for Reinforcement Learning","date":"2022-09-26","arxiv_id":"2209.12483","repositories_listed":0,"syntology":null},{"url":null,"slug":"overcoming-referential-ambiguity-in-language","title":"Overcoming Referential Ambiguity in Language-Guided Goal-Conditioned Reinforcement Learning","date":"2022-09-26","arxiv_id":"2209.12758","repositories_listed":0,"syntology":null}],"record_sha256":"63aa42824832033d49c8ab6ef59cfd5ef7f9cb917edbfff40645c1115da6fa1d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}