{"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/90","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":90,"pages_in_order":135,"rows_per_page":100,"rows":[8901,9000],"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/89","next":"/task/reinforcement-learning-2/papers/91","papers":[{"url":null,"slug":"learning-pseudometric-based-action","title":"Learning Pseudometric-based Action Representations for Offline Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-when-and-what-to-ask-a-hierarchical","title":"Learning When and What to Ask: a Hierarchical Reinforcement Learning Framework","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lpmarl-linear-programming-based-implicit-task","title":"LPMARL: Linear Programming based Implicit Task Assigment for Hiearchical Multi-Agent Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"marnet-backdoor-attacks-against-value","title":"MARNET: Backdoor Attacks against Value-Decomposition Multi-Agent Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"maximizing-ensemble-diversity-in-deep","title":"Maximizing Ensemble Diversity in Deep Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-attention-for-off-policy-actor-critic","title":"Meta Attention For Off-Policy Actor-Critic","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"metrics-matter-a-closer-look-on-self-paced","title":"Metrics Matter: A Closer Look on Self-Paced Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigation-of-adversarial-policy-imitation","title":"Mitigation of Adversarial Policy Imitation via Constrained Randomization of Policy (CRoP)","date":"2021-09-29","arxiv_id":"2109.14678","repositories_listed":0,"syntology":null},{"url":null,"slug":"moba-multi-teacher-model-based-reinforcement","title":"MOBA: Multi-teacher Model Based Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-reinforcement-learning-with-1","title":"Model-based Reinforcement Learning with Ensembled Model-value Expansion","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-with-2","title":"Multi-Agent Reinforcement Learning with Shared Resource in Inventory Management","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-batch-reinforcement-learning-via-sample","title":"Multi-batch Reinforcement Learning via Sample Transfer and Imitation Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"muro-deployment-constrained-reinforcement","title":"MURO: Deployment Constrained Reinforcement Learning with Model-based Uncertainty Regularized Batch Optimization","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nested-policy-reinforcement-learning-for","title":"Nested Policy Reinforcement Learning for Clinical Decision Support","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-combinatorial-optimization-with-1","title":"Neural Combinatorial Optimization with Reinforcement Learning : Solving theVehicle Routing Problem with Time Windows","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-online-reinforcement-learning","title":"Offline-Online Reinforcement Learning: Extending Batch and Online RL","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-pre-trained-multi-agent-decision","title":"Offline Pre-trained Multi-Agent Decision Transformer","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-reinforcement-learning-for-large","title":"Offline Reinforcement Learning for Large Scale Language Action Spaces","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-reinforcement-learning-with-resource","title":"Offline Reinforcement Learning with Resource Constrained Online Deployment","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"online-robust-reinforcement-learning-with","title":"Online Robust Reinforcement Learning with Model Uncertainty","date":"2021-09-29","arxiv_id":"2109.14523","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-tuning-for-offline-decentralized-multi","title":"Online Tuning for Offline Decentralized Multi-Agent Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ovd-explorer-a-general-information-theoretic","title":"OVD-Explorer: A General Information-theoretic Exploration Approach for Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"p4o-efficient-deep-reinforcement-learning","title":"P4O: Efficient Deep Reinforcement Learning with Predictive Processing Proximal Policy Optimization","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pareto-policy-adaptation","title":"Pareto Policy Adaptation","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pareto-policy-pool-for-model-based-offline","title":"Pareto Policy Pool for Model-based Offline Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pdqn-a-deep-reinforcement-learning-method-for","title":"PDQN - A Deep Reinforcement Learning Method for Planning with Long Delays: Optimization of Manufacturing Dispatching","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"polyphonic-music-composition-an-adversarial","title":"Polyphonic Music Composition: An Adversarial Inverse Reinforcement Learning Approach","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pretraining-for-language-conditioned","title":"Pretraining for Language Conditioned Imitation with Transformers","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"programmatic-reinforcement-learning-without","title":"Programmatic Reinforcement Learning without Oracles","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reachability-traces-for-curriculum-design-in","title":"Reachability Traces for Curriculum Design in Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-with-hierarchical-symbols","title":"Reasoning With Hierarchical Symbols: Reclaiming Symbolic Policies For Visual Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-state-estimation-for","title":"Reinforcement Learning State Estimation for High-Dimensional Nonlinear Systems","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-under-a-multi-agent","title":"Reinforcement Learning under a Multi-agent Predictive State Representation Model: Method and Theory","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-ex-post-max-min","title":"Reinforcement Learning with Ex-Post Max-Min Fairness","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-predictive","title":"Reinforcement Learning with Predictive Consistent Representations","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"research-on-fusion-algorithm-of-multi","title":"$$Research on fusion algorithm of multi-attribute decision making and reinforcement learning based on intuitionistic fuzzy number in wargame environment$$","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"resmax-an-alternative-soft-greedy-operator","title":"Resmax: An Alternative Soft-Greedy Operator for Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-pareto-approaches-in-constrained","title":"Rethinking Pareto Approaches in Constrained Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-the-monotonicity-constraint-in","title":"Revisiting the Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rewardless-open-ended-learning-roel","title":"Rewardless Open-Ended Learning (ROEL)","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-exploration-in-linear-equality","title":"Safe Exploration in Linear Equality Constraint","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"safer-data-efficient-and-safe-reinforcement","title":"SAFER: Data-Efficient and Safe Reinforcement Learning Through Skill Acquisition","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sbf-delta-2-exploration-for-reinforcement","title":"$\\sbf{\\delta^2}$-exploration for Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-structured-representations","title":"Self-Supervised Structured Representations for Deep Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-offline-reinforcement","title":"Semi-supervised Offline Reinforcement Learning with Pre-trained Decision Transformers","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sequential-communication-in-multi-agent","title":"Sequential Communication in Multi-Agent Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"should-i-run-offline-reinforcement-learning","title":"Should I Run Offline Reinforcement Learning or Behavioral Cloning?","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"spp-rl-state-planning-policy-reinforcement","title":"SPP-RL: State Planning Policy Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"stability-and-generalisation-in-batch","title":"Stability and Generalisation in Batch Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"state-action-joint-regularized-implicit","title":"State-Action Joint Regularized Implicit Policy for Offline Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"structure-aware-transformer-policy-for","title":"Structure-Aware Transformer Policy for Inhomogeneous Multi-Task Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"superior-performance-with-diversified","title":"Superior Performance with Diversified Strategic Control in FPS Games Using General Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"task-driven-discovery-of-perceptual-schemas","title":"Task-driven Discovery of Perceptual Schemas for Generalization in Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-essential-elements-of-offline-rl-via","title":"The Essential Elements of Offline RL via Supervised Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-remarkable-effectiveness-of-combining","title":"The Remarkable Effectiveness of Combining Policy and Value Networks in A*-based Deep RL for AI Planning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"theoretical-understanding-of-adversarial","title":"Theoretical understanding of adversarial reinforcement learning via mean-field optimal control","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-understanding-distributional-1","title":"Towards Understanding Distributional Reinforcement Learning: Regularization, Optimization, Acceleration and Sinkhorn Algorithm","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transformers-are-meta-reinforcement-learners","title":"Transformers are Meta-Reinforcement Learners","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-regularized-policy-learning-for","title":"Uncertainty Regularized Policy Learning for Offline Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-generalization-gap-in","title":"Understanding the Generalization Gap in Visual Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"untangling-braids-with-multi-agent-q-learning","title":"Untangling Braids with Multi-agent Q-Learning","date":"2021-09-29","arxiv_id":"2109.14502","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-oracle-guiding-for-reinforcement","title":"Variational oracle guiding for reinforcement learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"wavecorr-deep-reinforcement-learning-with","title":"WaveCorr: Deep Reinforcement Learning with Permutation Invariant Policy Networks for Portfolio Management","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-learning-of-disentangled","title":"Weakly-Supervised Learning of Disentangled and Interpretable Skills for Hierarchical Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"why-so-pessimistic-estimating-uncertainties","title":"Why so pessimistic? Estimating uncertainties for offline RL through ensembles, and why their independence matters.","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-first-occupancy-representation-for","title":"A First-Occupancy Representation for Reinforcement Learning","date":"2021-09-28","arxiv_id":"2109.13863","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-offline-deep-reinforcement-learning-for","title":"An Offline Deep Reinforcement Learning for Maintenance Decision-Making","date":"2021-09-28","arxiv_id":"2109.15050","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-versus-evolution","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","date":"2021-09-28","arxiv_id":"2110.01411","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-adjustments","title":"Deep Reinforcement Learning with Adjustments","date":"2021-09-28","arxiv_id":"2109.13463","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-more-when-it-needs-in-deep","title":"Exploring More When It Needs in Deep Reinforcement Learning","date":"2021-09-28","arxiv_id":"2109.13477","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-quantitative","title":"Reinforcement Learning for Quantitative Trading","date":"2021-09-28","arxiv_id":"2109.13851","repositories_listed":0,"syntology":null},{"url":null,"slug":"drl-based-slice-placement-under-realistic","title":"DRL-based Slice Placement under Realistic Network Load Conditions","date":"2021-09-27","arxiv_id":"2109.12857","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-internal-models-toward-metacognitive-ai","title":"From internal models toward metacognitive AI","date":"2021-09-27","arxiv_id":"2109.12798","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-free-reinforcement-learning-for-optimal","title":"Model-Free Reinforcement Learning for Optimal Control of MarkovDecision Processes Under Signal Temporal Logic Specifications","date":"2021-09-27","arxiv_id":"2109.13377","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-reinforcement-learning-for-pivot","title":"Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer","date":"2021-09-27","arxiv_id":"2109.13097","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-wireless-3","title":"Deep Reinforcement Learning for Wireless Scheduling in Distributed Networked Control","date":"2021-09-26","arxiv_id":"2109.12562","repositories_listed":0,"syntology":null},{"url":null,"slug":"l-2-nas-learning-to-optimize-neural","title":"L$^{2}$NAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learning","date":"2021-09-25","arxiv_id":"2109.12425","repositories_listed":0,"syntology":null},{"url":null,"slug":"combing-policy-evaluation-and-policy","title":"The $f$-Divergence Reinforcement Learning Framework","date":"2021-09-24","arxiv_id":"2109.11867","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-deep-reinforcement-learning-for-5","title":"Combining Contention-Based Spectrum Access and Adaptive Modulation using Deep Reinforcement Learning","date":"2021-09-24","arxiv_id":"2109.11723","repositories_listed":0,"syntology":null},{"url":null,"slug":"go-blend-behavior-and-affect","title":"Go-Blend behavior and affect","date":"2021-09-24","arxiv_id":"2109.13388","repositories_listed":0,"syntology":null},{"url":null,"slug":"learnable-triangulation-for-deep-learning","title":"Learnable Triangulation for Deep Learning-based 3D Reconstruction of Objects of Arbitrary Topology from Single RGB Images","date":"2021-09-24","arxiv_id":"2109.11844","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuroprospecting-with-deeprl-agents","title":"Neuroprospecting with DeepRL agents","date":"2021-09-24","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"regularization-guarantees-generalization-in","title":"Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability","date":"2021-09-24","arxiv_id":"2109.11792","repositories_listed":0,"syntology":null},{"url":null,"slug":"dimension-free-rates-for-natural-policy","title":"Dimension-Free Rates for Natural Policy Gradient in Multi-Agent Reinforcement Learning","date":"2021-09-23","arxiv_id":"2109.11692","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchies-of-planning-and-reinforcement","title":"Hierarchies of Planning and Reinforcement Learning for Robot Navigation","date":"2021-09-23","arxiv_id":"2109.11178","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-based-path-planning-for-long-range","title":"Deep Reinforcement Learning-Based Long-Range Autonomous Valet Parking for Smart Cities","date":"2021-09-23","arxiv_id":"2109.11661","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-under-algorithmic","title":"Reinforcement Learning Under Algorithmic Triage","date":"2021-09-23","arxiv_id":"2109.11328","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-reinforcement-learning-for-1","title":"A Survey on Reinforcement Learning for Recommender Systems","date":"2021-09-22","arxiv_id":"2109.10665","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-training-blocks-generalization-in","title":"Adversarial Training Blocks Generalization in Neural Policies","date":"2021-09-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-lane-changing-decision-making","title":"Benchmarking Lane-changing Decision-making for Deep Reinforcement Learning","date":"2021-09-22","arxiv_id":"2109.10490","repositories_listed":0,"syntology":null},{"url":null,"slug":"introducing-symmetries-to-black-box-meta","title":"Introducing Symmetries to Black Box Meta Reinforcement Learning","date":"2021-09-22","arxiv_id":"2109.10781","repositories_listed":0,"syntology":null},{"url":null,"slug":"locality-matters-a-scalable-value","title":"Locality Matters: A Scalable Value Decomposition Approach for Cooperative Multi-Agent Reinforcement Learning","date":"2021-09-22","arxiv_id":"2109.10632","repositories_listed":0,"syntology":null},{"url":null,"slug":"mepg-a-minimalist-ensemble-policy-gradient","title":"MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning","date":"2021-09-22","arxiv_id":"2109.10552","repositories_listed":0,"syntology":null},{"url":null,"slug":"return-dispersion-as-an-estimator-of-learning","title":"Return Dispersion as an Estimator of Learning Potential for Prioritized Level Replay","date":"2021-09-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-multi-agent-reinforcement-learning-1","title":"Towards Multi-Agent Reinforcement Learning using Quantum Boltzmann Machines","date":"2021-09-22","arxiv_id":"2109.10900","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-unified-framework-for-anomaly","title":"A Distance-based Anomaly Detection Framework for Deep Reinforcement Learning","date":"2021-09-21","arxiv_id":"2109.09889","repositories_listed":0,"syntology":null},{"url":null,"slug":"example-driven-model-based-reinforcement","title":"Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Tasks","date":"2021-09-21","arxiv_id":"2109.10312","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-offline-memory-replay-in-biological","title":"Learning offline: memory replay in biological and artificial reinforcement learning","date":"2021-09-21","arxiv_id":"2109.10034","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-approach-to-the-1","title":"A Reinforcement Learning Approach to the Stochastic Cutting Stock Problem","date":"2021-09-20","arxiv_id":"2109.09592","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-text-games-for-reinforcement","title":"A Survey of Text Games for Reinforcement Learning informed by Natural Language","date":"2021-09-20","arxiv_id":"2109.09478","repositories_listed":0,"syntology":null}],"record_sha256":"9854dc2db0eda54e686ce446222db33e45fa949a4ecd0464838015d81d3f26de","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}