{"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/papers/83","list_of":"/task/reinforcement-learning","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":83,"pages_in_order":132,"rows_per_page":100,"rows":[8201,8300],"of":13178,"counts":{"archive_papers_tagged":13178,"with_a_code_link":4183,"where_syntology_ran_a_sample":1175,"not_listed_spam_title":0,"listed":13178,"listed_where_code_ran":1175,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":988,"every_run_a_failure_of_syntologys_instrument":187,"listed_with_a_run_with_no_instrument_failure":988,"listed_every_run_a_failure_of_syntologys_instrument":187,"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","prev":"/task/reinforcement-learning/papers/82","next":"/task/reinforcement-learning/papers/84","papers":[{"url":null,"slug":"intrinsically-motivated-self-supervised","title":"Intrinsically Motivated Self-supervised Learning in Reinforcement Learning","date":"2021-06-26","arxiv_id":"2106.13970","repositories_listed":0,"syntology":null},{"url":null,"slug":"balancing-accuracy-and-fairness-for","title":"Balancing Accuracy and Fairness for Interactive Recommendation with Reinforcement Learning","date":"2021-06-25","arxiv_id":"2106.13386","repositories_listed":0,"syntology":null},{"url":null,"slug":"branch-prediction-as-a-reinforcement-learning","title":"Branch Prediction as a Reinforcement Learning Problem: Why, How and Case Studies","date":"2021-06-25","arxiv_id":"2106.13429","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-mean-field-games","title":"Reinforcement Learning for Mean Field Games, with Applications to Economics","date":"2021-06-25","arxiv_id":"2106.13755","repositories_listed":0,"syntology":null},{"url":null,"slug":"density-constrained-reinforcement-learning-1","title":"Density Constrained Reinforcement Learning","date":"2021-06-24","arxiv_id":"2106.12764","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-robot-deep-reinforcement-learning-for","title":"Hierarchically Integrated Models: Learning to Navigate from Heterogeneous Robots","date":"2021-06-24","arxiv_id":"2106.13280","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-option-keyboard-combining-skills-in-1","title":"The Option Keyboard: Combining Skills in Reinforcement Learning","date":"2021-06-24","arxiv_id":"2106.13105","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolving-hierarchical-memory-prediction","title":"Evolving Hierarchical Memory-Prediction Machines in Multi-Task Reinforcement Learning","date":"2021-06-23","arxiv_id":"2106.12659","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-framework-for-conservative","title":"A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning","date":"2021-06-22","arxiv_id":"2106.11692","repositories_listed":0,"syntology":null},{"url":null,"slug":"agnostic-reinforcement-learning-with-low-rank","title":"Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations","date":"2021-06-22","arxiv_id":"2106.11519","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmd-mix-value-function-factorisation-with","title":"MMD-MIX: Value Function Factorisation with Maximum Mean Discrepancy for Cooperative Multi-Agent Reinforcement Learning","date":"2021-06-22","arxiv_id":"2106.11652","repositories_listed":0,"syntology":null},{"url":null,"slug":"off-policy-reinforcement-learning-with","title":"Off-Policy Reinforcement Learning with Delayed Rewards","date":"2021-06-22","arxiv_id":"2106.11854","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-efficient-representation-learning-in","title":"Provably Efficient Representation Selection in Low-rank Markov Decision Processes: From Online to Offline RL","date":"2021-06-22","arxiv_id":"2106.11935","repositories_listed":0,"syntology":null},{"url":null,"slug":"uniform-pac-bounds-for-reinforcement-learning","title":"Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation","date":"2021-06-22","arxiv_id":"2106.11612","repositories_listed":0,"syntology":null},{"url":null,"slug":"analytically-tractable-bayesian-deep-q","title":"Analytically Tractable Bayesian Deep Q-Learning","date":"2021-06-21","arxiv_id":"2106.11086","repositories_listed":0,"syntology":null},{"url":null,"slug":"emphatic-algorithms-for-deep-reinforcement","title":"Emphatic Algorithms for Deep Reinforcement Learning","date":"2021-06-21","arxiv_id":"2106.11779","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-model-based-hierarchical","title":"Interpretable Model-based Hierarchical Reinforcement Learning using Inductive Logic Programming","date":"2021-06-21","arxiv_id":"2106.11417","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-smoothing-for-provably-robust","title":"Policy Smoothing for Provably Robust Reinforcement Learning","date":"2021-06-21","arxiv_id":"2106.11420","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-offline-reinforcement-learning-with","title":"Boosting Offline Reinforcement Learning with Residual Generative Modeling","date":"2021-06-19","arxiv_id":"2106.10411","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-learning-for-robust-fitting-a-1","title":"Unsupervised Learning for Robust Fitting: A Reinforcement Learning Approach","date":"2021-06-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarially-trained-neural-policies-in-the","title":"Adversarially Trained Neural Policies in the Fourier Domain","date":"2021-06-18","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-models-predict","title":"Deep Reinforcement Learning Models Predict Visual Responses in the Brain: A Preliminary Result","date":"2021-06-18","arxiv_id":"2106.10112","repositories_listed":0,"syntology":null},{"url":null,"slug":"goal-directed-planning-by-reinforcement","title":"Goal-Directed Planning by Reinforcement Learning and Active Inference","date":"2021-06-18","arxiv_id":"2106.09938","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-robust-feature-mapping-in-deep","title":"Non-Robust Feature Mapping in Deep Reinforcement Learning","date":"2021-06-18","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-sample-complexity-of-batch","title":"The Curse of Passive Data Collection in Batch Reinforcement Learning","date":"2021-06-18","arxiv_id":"2106.09973","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-efficient-social-navigation-using","title":"Sample Efficient Social Navigation Using Inverse Reinforcement Learning","date":"2021-06-18","arxiv_id":"2106.10318","repositories_listed":0,"syntology":null},{"url":null,"slug":"scenic4rl-programmatic-modeling-and","title":"Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environments","date":"2021-06-18","arxiv_id":"2106.10365","repositories_listed":0,"syntology":null},{"url":null,"slug":"strategically-timed-state-observation-attacks","title":"Strategically-timed State-Observation Attacks on Deep Reinforcement Learning Agents","date":"2021-06-18","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-approach-for-an-irs","title":"A Reinforcement Learning Approach for an IRS-assisted NOMA Network","date":"2021-06-17","arxiv_id":"2106.09611","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-the-function-approximation","title":"Adapting the Function Approximation Architecture in Online Reinforcement Learning","date":"2021-06-17","arxiv_id":"2106.09776","repositories_listed":0,"syntology":null},{"url":null,"slug":"many-agent-reinforcement-learning-under","title":"Many Agent Reinforcement Learning Under Partial Observability","date":"2021-06-17","arxiv_id":"2106.09825","repositories_listed":0,"syntology":null},{"url":null,"slug":"modelling-resource-allocation-in-uncertain","title":"Modelling resource allocation in uncertain system environment through deep reinforcement learning","date":"2021-06-17","arxiv_id":"2106.09461","repositories_listed":0,"syntology":null},{"url":null,"slug":"mungojerrie-reinforcement-learning-of-linear","title":"Mungojerrie: Reinforcement Learning of Linear-Time Objectives","date":"2021-06-16","arxiv_id":"2106.09161","repositories_listed":0,"syntology":null},{"url":null,"slug":"unbiased-methods-for-multi-goal-reinforcement","title":"Unbiased Methods for Multi-Goal Reinforcement Learning","date":"2021-06-16","arxiv_id":"2106.08863","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-on-a-multi-asset","title":"Deep reinforcement learning on a multi-asset environment for trading","date":"2021-06-15","arxiv_id":"2106.08437","repositories_listed":0,"syntology":null},{"url":null,"slug":"fundamental-limits-of-reinforcement-learning","title":"Fundamental Limits of Reinforcement Learning in Environment with Endogeneous and Exogeneous Uncertainty","date":"2021-06-15","arxiv_id":"2106.08477","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimizing-communication-while-maximizing","title":"Minimizing Communication while Maximizing Performance in Multi-Agent Reinforcement Learning","date":"2021-06-15","arxiv_id":"2106.08482","repositories_listed":0,"syntology":null},{"url":null,"slug":"residual-reinforcement-learning-from","title":"Residual Reinforcement Learning from Demonstrations","date":"2021-06-15","arxiv_id":"2106.08050","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-policy-deep-reinforcement-learning-for-the","title":"On-Policy Deep Reinforcement Learning for the Average-Reward Criterion","date":"2021-06-14","arxiv_id":"2106.07329","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-sub-sampling-for-reinforcement","title":"Online Sub-Sampling for Reinforcement Learning with General Function Approximation","date":"2021-06-14","arxiv_id":"2106.07203","repositories_listed":0,"syntology":null},{"url":null,"slug":"poisoning-deep-reinforcement-learning-agents","title":"Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers","date":"2021-06-14","arxiv_id":"2106.07798","repositories_listed":0,"syntology":null},{"url":null,"slug":"targeted-data-acquisition-for-evolving","title":"Targeted Data Acquisition for Evolving Negotiation Agents","date":"2021-06-14","arxiv_id":"2106.07728","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-like-playing-a-reinforcement","title":"Training like Playing: A Reinforcement Learning And Knowledge Graph-based framework for building Automatic Consultation System in Medical Field","date":"2021-06-14","arxiv_id":"2106.07502","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-soft-computing-method-for-integration","title":"A new soft computing method for integration of expert's knowledge in reinforcement learn-ing problems","date":"2021-06-13","arxiv_id":"2106.07088","repositories_listed":0,"syntology":null},{"url":null,"slug":"bellman-consistent-pessimism-for-offline","title":"Bellman-consistent Pessimism for Offline Reinforcement Learning","date":"2021-06-13","arxiv_id":"2106.06926","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangled-predictive-representation-for","title":"Disentangled Predictive Representation for Meta-Reinforcement Learning","date":"2021-06-13","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-driven-representation-learning-in","title":"Exploration-Driven Representation Learning in Reinforcement Learning","date":"2021-06-13","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-task-relevant-representations-with","title":"Learning Task-Relevant Representations with Selective Contrast for Reinforcement Learning in a Real-World Application","date":"2021-06-13","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-explore-multiple-environments","title":"Learning to Explore Multiple Environments without Rewards","date":"2021-06-13","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"masai-multi-agent-summative-assessment","title":"MASAI: Multi-agent Summative Assessment Improvement for Unsupervised Environment Design","date":"2021-06-13","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-learning-for-out-of-1","title":"Representation Learning for Out-of-distribution Generalization in Reinforcement Learning","date":"2021-06-13","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tangent-space-least-adaptive-clustering","title":"Tangent Space Least Adaptive Clustering","date":"2021-06-13","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"model-free-reinforcement-learning-for-2","title":"Model-free Reinforcement Learning for Branching Markov Decision Processes","date":"2021-06-12","arxiv_id":"2106.06777","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-risk-adaptation-in-distributional","title":"Automatic Risk Adaptation in Distributional Reinforcement Learning","date":"2021-06-11","arxiv_id":"2106.06317","repositories_listed":0,"syntology":null},{"url":null,"slug":"corruption-robust-offline-reinforcement","title":"Corruption-Robust Offline Reinforcement Learning","date":"2021-06-11","arxiv_id":"2106.06630","repositories_listed":0,"syntology":null},{"url":null,"slug":"courteous-behavior-of-automated-vehicles-at","title":"Courteous Behavior of Automated Vehicles at Unsignalized Intersections via Reinforcement Learning","date":"2021-06-11","arxiv_id":"2106.06369","repositories_listed":0,"syntology":null},{"url":null,"slug":"decore-deep-compression-with-reinforcement","title":"DECORE: Deep Compression with Reinforcement Learning","date":"2021-06-11","arxiv_id":"2106.06091","repositories_listed":0,"syntology":null},{"url":"/paper/gdi-rethinking-what-makes-reinforcement","slug":"gdi-rethinking-what-makes-reinforcement","title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","date":"2021-06-11","arxiv_id":"2106.06232","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-reinforcement-learning-as-anti","title":"Offline Reinforcement Learning as Anti-Exploration","date":"2021-06-11","arxiv_id":"2106.06431","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-reinforcement-learning-with-linear","title":"Safe Reinforcement Learning with Linear Function Approximation","date":"2021-06-11","arxiv_id":"2106.06239","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-battery-operation-for-energy","title":"Data-driven battery operation for energy arbitrage using rainbow deep reinforcement learning","date":"2021-06-10","arxiv_id":"2106.06061","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperspace-neighbor-penetration-approach-to","title":"Hyperspace Neighbor Penetration Approach to Dynamic Programming for Model-Based Reinforcement Learning Problems with Slowly Changing Variables in A Continuous State Space","date":"2021-06-10","arxiv_id":"2106.05497","repositories_listed":0,"syntology":null},{"url":null,"slug":"rlcorrector-reinforced-proofreading-for","title":"RLCorrector: Reinforced Proofreading for Cell-level Microscopy Image Segmentation","date":"2021-06-10","arxiv_id":"2106.05487","repositories_listed":0,"syntology":null},{"url":null,"slug":"deception-in-social-learning-a-multi-agent","title":"Deception in Social Learning: A Multi-Agent Reinforcement Learning Perspective","date":"2021-06-09","arxiv_id":"2106.05402","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-inverse-reinforcement-learning","title":"Offline Inverse Reinforcement Learning","date":"2021-06-09","arxiv_id":"2106.05068","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-learning-for-stochastic-shortest-path","title":"Online Learning for Stochastic Shortest Path Model via Posterior Sampling","date":"2021-06-09","arxiv_id":"2106.05335","repositories_listed":0,"syntology":null},{"url":null,"slug":"over-the-fiber-digital-predistortion-using","title":"Over-the-fiber Digital Predistortion Using Reinforcement Learning","date":"2021-06-09","arxiv_id":"2106.04934","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-finetuning-bridging-sample-efficient","title":"Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning","date":"2021-06-09","arxiv_id":"2106.04895","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-industrial-control","title":"Reinforcement Learning for Industrial Control Network Cyber Security Orchestration","date":"2021-06-09","arxiv_id":"2106.05332","repositories_listed":0,"syntology":null},{"url":null,"slug":"don-t-get-yourself-into-trouble-risk-aware","title":"Don't Get Yourself into Trouble! Risk-aware Decision-Making for Autonomous Vehicles","date":"2021-06-08","arxiv_id":"2106.04625","repositories_listed":0,"syntology":null},{"url":null,"slug":"rewardsofsum-exploring-reinforcement-learning","title":"RewardsOfSum: Exploring Reinforcement Learning Rewards for Summarisation","date":"2021-06-08","arxiv_id":"2106.04080","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-practical-credit-assignment-for-deep","title":"Towards Practical Credit Assignment for Deep Reinforcement Learning","date":"2021-06-08","arxiv_id":"2106.04499","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-computational-model-of-representation","title":"A Computational Model of Representation Learning in the Brain Cortex, Integrating Unsupervised and Reinforcement Learning","date":"2021-06-07","arxiv_id":"2106.03688","repositories_listed":0,"syntology":null},{"url":null,"slug":"average-reward-reinforcement-learning-with-2","title":"Average-Reward Reinforcement Learning with Trust Region Methods","date":"2021-06-07","arxiv_id":"2106.03442","repositories_listed":0,"syntology":null},{"url":null,"slug":"concave-utility-reinforcement-learning-the","title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","date":"2021-06-07","arxiv_id":"2106.03787","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifiability-in-inverse-reinforcement","title":"Identifiability in inverse reinforcement learning","date":"2021-06-07","arxiv_id":"2106.03498","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-guide-a-saturation-based-theorem","title":"Learning to Guide a Saturation-Based Theorem Prover","date":"2021-06-07","arxiv_id":"2106.03906","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-without-knowing-unobserved-context","title":"Learning without Knowing: Unobserved Context in Continuous Transfer Reinforcement Learning","date":"2021-06-07","arxiv_id":"2106.03833","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-battery-storage-management-using","title":"Multi-agent Battery Storage Management using MPC-based Reinforcement Learning","date":"2021-06-07","arxiv_id":"2106.03541","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-robust-and-domain-agnostic","title":"Towards robust and domain agnostic reinforcement learning competitions","date":"2021-06-07","arxiv_id":"2106.03748","repositories_listed":0,"syntology":null},{"url":null,"slug":"distop-discovering-a-topological","title":"DisTop: Discovering a Topological representation to learn diverse and rewarding skills","date":"2021-06-06","arxiv_id":"2106.03853","repositories_listed":0,"syntology":null},{"url":null,"slug":"heuristic-guided-reinforcement-learning","title":"Heuristic-Guided Reinforcement Learning","date":"2021-06-05","arxiv_id":"2106.02757","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-routines-for-effective-off-policy","title":"Learning Routines for Effective Off-Policy Reinforcement Learning","date":"2021-06-05","arxiv_id":"2106.02943","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-assignment-problem-1","title":"Reinforcement Learning for Assignment Problem with Time Constraints","date":"2021-06-05","arxiv_id":"2106.02856","repositories_listed":0,"syntology":null},{"url":null,"slug":"nara-learning-network-aware-resource","title":"Resource Allocation in Disaggregated Data Centre Systems with Reinforcement Learning","date":"2021-06-04","arxiv_id":"2106.02412","repositories_listed":0,"syntology":null},{"url":null,"slug":"robustifying-reinforcement-learning-policies","title":"Robustifying Reinforcement Learning Policies with $\\mathcal{L}_1$ Adaptive Control","date":"2021-06-04","arxiv_id":"2106.02249","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperbolically-discounted-reinforcement","title":"Hyperbolically-Discounted Reinforcement Learning on Reward-Punishment Framework","date":"2021-06-03","arxiv_id":"2106.01516","repositories_listed":0,"syntology":null},{"url":null,"slug":"limiirl-lightweight-multiple-intent-inverse","title":"LiMIIRL: Lightweight Multiple-Intent Inverse Reinforcement Learning","date":"2021-06-03","arxiv_id":"2106.01777","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-ran-control-a-symbolic-reinforcement","title":"Safe RAN control: A Symbolic Reinforcement Learning Approach","date":"2021-06-03","arxiv_id":"2106.01977","repositories_listed":0,"syntology":null},{"url":null,"slug":"expected-scalarised-returns-dominance-a-new","title":"Expected Scalarised Returns Dominance: A New Solution Concept for Multi-Objective Decision Making","date":"2021-06-02","arxiv_id":"2106.01048","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-deeper-deep-reinforcement-learning","title":"Towards Deeper Deep Reinforcement Learning with Spectral Normalization","date":"2021-06-02","arxiv_id":"2106.01151","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-empowerment-as-representation","title":"Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning","date":"2021-06-02","arxiv_id":"2106.01404","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-coarse-to-fine-question-answering-system","title":"A Coarse to Fine Question Answering System based on Reinforcement Learning","date":"2021-06-01","arxiv_id":"2106.00257","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-entropy-regularization-free-mechanism-for","title":"An Entropy Regularization Free Mechanism for Policy-based Reinforcement Learning","date":"2021-06-01","arxiv_id":"2106.00707","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantitative-day-trading-from-natural","title":"Quantitative Day Trading from Natural Language using Reinforcement Learning","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforce-security-a-model-free-approach","title":"Reinforce Security: A Model-Free Approach Towards Secure Wiretap Coding","date":"2021-06-01","arxiv_id":"2106.00343","repositories_listed":0,"syntology":null},{"url":null,"slug":"shapley-counterfactual-credits-for-multi","title":"Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning","date":"2021-06-01","arxiv_id":"2106.00285","repositories_listed":0,"syntology":null},{"url":null,"slug":"procedural-content-generation-better","title":"Procedural Content Generation: Better Benchmarks for Transfer Reinforcement Learning","date":"2021-05-31","arxiv_id":"2105.14780","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-dynamic-service","title":"Reinforcement Learning-based Dynamic Service Placement in Vehicular Networks","date":"2021-05-31","arxiv_id":"2105.15022","repositories_listed":0,"syntology":null},{"url":null,"slug":"tesseract-tensorised-actors-for-multi-agent","title":"Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning","date":"2021-05-31","arxiv_id":"2106.00136","repositories_listed":0,"syntology":null}],"record_sha256":"d5fa4c48a87e8615634667ffa3d1cac479e9f81bbf440818b5d5c2589b7a0051","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}