{"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-1/papers/98","list_of":"/task/reinforcement-learning-1","task":"Reinforcement Learning (RL)","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":98,"pages_in_order":152,"rows_per_page":100,"rows":[9701,9800],"of":15113,"counts":{"archive_papers_tagged":15113,"with_a_code_link":4749,"where_syntology_ran_a_sample":1416,"not_listed_spam_title":0,"listed":15113,"listed_where_code_ran":1416,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1186,"every_run_a_failure_of_syntologys_instrument":230,"listed_with_a_run_with_no_instrument_failure":1186,"listed_every_run_a_failure_of_syntologys_instrument":230,"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-1","prev":"/task/reinforcement-learning-1/papers/97","next":"/task/reinforcement-learning-1/papers/99","papers":[{"url":null,"slug":"distributional-reinforcement-learning-with-5","title":"Distributional Reinforcement Learning with Monotonic Splines","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dsdf-coordinated-look-ahead-strategy-in","title":"DSDF: Coordinated look-ahead strategy in stochastic multi-agent reinforcement learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"eat-c-environment-adversarial-sub-task","title":"EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"effects-of-conservatism-on-offline-learning","title":"Effects of Conservatism on Offline Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-reinforcement-learning","title":"Efficient Reinforcement Learning Experimentation in PyTorch","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-wasserstein-and-sinkhorn-policy","title":"Efficient Wasserstein and Sinkhorn Policy Optimization","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"eqr-equivariant-representations-for-data","title":"EqR: Equivariant Representations for Data-Efficient Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-robustness-of-cooperative-marl","title":"Evaluating Robustness of Cooperative MARL","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evolution-strategies-as-an-alternate-learning","title":"Evolution Strategies as an Alternate Learning method for Hierarchical Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evolutionary-diversity-optimization-with","title":"Evolutionary Diversity Optimization with Clustering-based Selection for Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"experience-replay-more-when-it-s-a-key","title":"Experience Replay More When It's a Key Transition in Deep Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-robustness-of-distributional-1","title":"Exploring the Robustness of Distributional Reinforcement Learning against Noisy State Observations","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-reinforcement-learning-with-value","title":"Faster Reinforcement Learning with Value Target Lower Bounding","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"finite-time-convergence-and-sample-complexity","title":"Finite-Time Convergence and Sample Complexity of Multi-Agent Actor-Critic Reinforcement Learning with Average Reward","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"formulation-and-validation-of-a-car-following","title":"Formulation and validation of a car-following model based on deep reinforcement learning","date":"2021-09-29","arxiv_id":"2109.14268","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-decentralized-model-based-policy","title":"Fully Decentralized Model-based Policy Optimization with Networked Agents","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generalisation-in-lifelong-reinforcement","title":"Generalisation in Lifelong Reinforcement Learning through Logical Composition","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-maximum-entropy-reinforcement","title":"Generalized Maximum Entropy Reinforcement Learning via Reward Shaping","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizing-successor-features-to-continuous","title":"Generalizing Successor Features to continuous domains for Multi-task Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-enhanced-exploration-for-goal-oriented","title":"Graph-Enhanced Exploration for Goal-oriented Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"greedy-based-value-representation-for","title":"Greedy-based Value Representation for Efficient Coordination in Multi-agent Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hypothesis-driven-coordinate-ascent-for","title":"Hypothesis Driven Coordinate Ascent for Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ia-marl-imputation-assisted-multi-agent","title":"IA-MARL: Imputation Assisted Multi-Agent Reinforcement Learning for Missing Training Data","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-safety-in-deep-reinforcement","title":"Improving Safety in Deep Reinforcement Learning using Unsupervised Action Planning","date":"2021-09-29","arxiv_id":"2109.14325","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-bottleneck-based-behavior","title":"Information-Bottleneck-Based Behavior Representation Learning for Multi-agent Reinforcement learning","date":"2021-09-29","arxiv_id":"2109.14188","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpreting-reinforcement-policies-through","title":"Interpreting Reinforcement Policies through Local Behaviors","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-self-supervised-learning-for-vision","title":"Joint Self-Supervised Learning for Vision-based Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-controllable-elements-oriented","title":"Learning Controllable Elements Oriented Representations for Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-invariant-reward-functions-through","title":"Learning Invariant Reward Functions through Trajectory Interventions","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"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-to-solve-combinatorial-problems-via","title":"Learning to Solve Combinatorial Problems via Efficient Exploration","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":"on-reward-maximization-and-distribution","title":"On Reward Maximization and Distribution Matching for Fine-Tuning Language Models","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-benefits-of-deep-rl-in-accelerated-mri","title":"On the benefits of deep RL in accelerated MRI sampling","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":"/paper/particle-based-stochastic-policy-optimization","slug":"particle-based-stochastic-policy-optimization","title":"Particle Based Stochastic Policy Optimization","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":"plan-your-target-and-learn-your-skills-state","title":"Plan Your Target and Learn Your Skills: State-Only Imitation Learning via Decoupled Policy Optimization","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":"provably-filtering-exogenous-distractors","title":"Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics","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":"selective-token-generation-for-few-shot","title":"Selective Token Generation for Few-shot Language Modeling","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":"targeted-environment-design-from-offline-data","title":"Targeted Environment Design from Offline Data","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":"text-generation-with-efficient-soft-q-1","title":"Text Generation with Efficient (Soft) $Q$-Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"that-escalated-quickly-compounding-complexity","title":"That Escalated Quickly: Compounding Complexity by Editing Levels at the Frontier of Agent Capabilities","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-guide-and-the-explorer-smart-agents-for","title":"The guide and the explorer: smart agents for resource-limited iterated batch reinforcement 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":"towards-unknown-aware-deep-q-learning","title":"Towards Unknown-aware Deep Q-Learning","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":"triangular-dropout-variable-network-width","title":"Triangular Dropout: Variable Network Width without Retraining","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"7e132a478e6b2419bb9e88d4177b93dc4fcb1b54341f61acb229cb971256a426","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}