{"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/hierarchical-reinforcement-learning/papers/3","list_of":"/task/hierarchical-reinforcement-learning","task":"Hierarchical 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":3,"pages_in_order":4,"rows_per_page":100,"rows":[201,300],"of":384,"counts":{"archive_papers_tagged":384,"with_a_code_link":111,"where_syntology_ran_a_sample":22,"not_listed_spam_title":0,"listed":384,"listed_where_code_ran":22,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":22,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":22,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/hierarchical-reinforcement-learning","prev":"/task/hierarchical-reinforcement-learning/papers/2","next":"/task/hierarchical-reinforcement-learning/papers/4","papers":[{"url":null,"slug":"co-learning-planning-and-control-policies","title":"Co-learning Planning and Control Policies Constrained by Differentiable Logic Specifications","date":"2023-03-02","arxiv_id":"2303.01346","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-in","title":"Hierarchical Reinforcement Learning in Complex 3D Environments","date":"2023-02-28","arxiv_id":"2302.14451","repositories_listed":0,"syntology":null},{"url":null,"slug":"conditioning-hierarchical-reinforcement","title":"Handling Long and Richly Constrained Tasks through Constrained Hierarchical Reinforcement Learning","date":"2023-02-21","arxiv_id":"2302.10639","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-learning-with-unsupervised-skill","title":"Developing Driving Strategies Efficiently: A Skill-Based Hierarchical Reinforcement Learning Approach","date":"2023-02-04","arxiv_id":"2302.02179","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-for-ris","title":"Hierarchical Reinforcement Learning for RIS-Assisted Energy-Efficient RAN","date":"2023-01-07","arxiv_id":"2301.02771","repositories_listed":0,"syntology":null},{"url":null,"slug":"shiro-soft-hierarchical-reinforcement","title":"SHIRO: Soft Hierarchical Reinforcement Learning","date":"2022-12-24","arxiv_id":"2212.12786","repositories_listed":0,"syntology":null},{"url":null,"slug":"explaining-agent-s-decision-making-in-a","title":"Explaining Agent's Decision-making in a Hierarchical Reinforcement Learning Scenario","date":"2022-12-14","arxiv_id":"2212.06967","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-deep-reinforcement-learning-for-1","title":"Hierarchical Deep Reinforcement Learning for VWAP Strategy Optimization","date":"2022-12-11","arxiv_id":"2212.14670","repositories_listed":0,"syntology":null},{"url":null,"slug":"planning-irregular-object-packing-via","title":"Planning Irregular Object Packing via Hierarchical Reinforcement Learning","date":"2022-11-17","arxiv_id":"2211.09382","repositories_listed":0,"syntology":null},{"url":null,"slug":"emergency-action-termination-for-immediate","title":"Emergency action termination for immediate reaction in hierarchical reinforcement learning","date":"2022-11-11","arxiv_id":"2211.06351","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-for-7","title":"Hierarchical Reinforcement Learning for Furniture Layout in Virtual Indoor Scenes","date":"2022-10-19","arxiv_id":"2210.10431","repositories_listed":0,"syntology":null},{"url":null,"slug":"avlen-audio-visual-language-embodied","title":"AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments","date":"2022-10-14","arxiv_id":"2210.07940","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":"optimizing-industrial-hvac-systems-with","title":"Optimizing Industrial HVAC Systems with Hierarchical Reinforcement Learning","date":"2022-09-16","arxiv_id":"2209.08112","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-coupled-mechanisms-a-control-method","title":"Causal Coupled Mechanisms: A Control Method with Cooperation and Competition for Complex System","date":"2022-09-15","arxiv_id":"2209.07368","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-based","title":"Hierarchical Reinforcement Learning Based Video Semantic Coding for Segmentation","date":"2022-08-24","arxiv_id":"2208.11529","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-problem-solving-as-integrated","title":"Intelligent problem-solving as integrated hierarchical reinforcement learning","date":"2022-08-18","arxiv_id":"2208.08731","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-for-6","title":"Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot","date":"2022-08-01","arxiv_id":"2208.01160","repositories_listed":0,"syntology":null},{"url":null,"slug":"flowsheet-synthesis-through-hierarchical","title":"Flowsheet synthesis through hierarchical reinforcement learning and graph neural networks","date":"2022-07-25","arxiv_id":"2207.12051","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-decision-making-at-the-intersection","title":"Adaptive Decision Making at the Intersection for Autonomous Vehicles Based on Skill Discovery","date":"2022-07-24","arxiv_id":"2207.11724","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-temporally-extended-skills-in","title":"Learning Temporally Extended Skills in Continuous Domains as Symbolic Actions for Planning","date":"2022-07-11","arxiv_id":"2207.05018","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-with-4","title":"Hierarchical Reinforcement Learning with Opponent Modeling for Distributed Multi-agent Cooperation","date":"2022-06-25","arxiv_id":"2206.12718","repositories_listed":0,"syntology":null},{"url":null,"slug":"matching-options-to-tasks-using-option","title":"Matching options to tasks using Option-Indexed Hierarchical Reinforcement Learning","date":"2022-06-12","arxiv_id":"2206.05750","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-inference-and-transfer-of-compositional","title":"Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization","date":"2022-05-25","arxiv_id":"2205.12648","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-learning-approach-for-joint-design-of-event","title":"A Learning Approach for Joint Design of Event-triggered Control and Power-Efficient Resource Allocation","date":"2022-05-14","arxiv_id":"2205.07070","repositories_listed":0,"syntology":null},{"url":null,"slug":"developing-cooperative-policies-for-multi-1","title":"Developing cooperative policies for multi-stage reinforcement learning tasks","date":"2022-05-11","arxiv_id":"2205.05230","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-how-to-interact-with-a-complex","title":"Learning how to Interact with a Complex Interface using Hierarchical Reinforcement Learning","date":"2022-04-21","arxiv_id":"2204.10374","repositories_listed":0,"syntology":null},{"url":null,"slug":"rl4real-reinforcement-learning-for-register","title":"RL4ReAl: Reinforcement Learning for Register Allocation","date":"2022-04-05","arxiv_id":"2204.02013","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-asynchronous-cooperation-with","title":"Asynchronous, Option-Based Multi-Agent Policy Gradient: A Conditional Reasoning Approach","date":"2022-03-29","arxiv_id":"2203.15925","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-of","title":"Hierarchical Reinforcement Learning of Locomotion Policies in Response to Approaching Objects: A Preliminary Study","date":"2022-03-20","arxiv_id":"2203.10616","repositories_listed":0,"syntology":null},{"url":null,"slug":"firl-fast-imitation-and-policy-reuse-learning","title":"A Versatile Agent for Fast Learning from Human Instructors","date":"2022-03-01","arxiv_id":"2203.00251","repositories_listed":0,"syntology":null},{"url":null,"slug":"robots-learn-increasingly-complex-tasks-with","title":"Robots Learn Increasingly Complex Tasks with Intrinsic Motivation and Automatic Curriculum Learning","date":"2022-02-11","arxiv_id":"2202.10222","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarially-guided-subgoal-generation-for","title":"State-Conditioned Adversarial Subgoal Generation","date":"2022-01-24","arxiv_id":"2201.09635","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-family-of-cognitively-realistic-parsing","title":"A Family of Cognitively Realistic Parsing Environments for Deep Reinforcement Learning","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-1","title":"Deep Reinforcement Learning, a textbook","date":"2022-01-04","arxiv_id":"2201.02135","repositories_listed":0,"syntology":null},{"url":null,"slug":"juewu-mc-playing-minecraft-with-sample","title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning","date":"2021-12-07","arxiv_id":"2112.04907","repositories_listed":0,"syntology":null},{"url":null,"slug":"selectaugment-hierarchical-deterministic","title":"SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation","date":"2021-12-06","arxiv_id":"2112.02862","repositories_listed":0,"syntology":null},{"url":null,"slug":"personal-comfort-estimation-in-partial","title":"Towards Personalization of User Preferences in Partially Observable Smart Home Environments","date":"2021-12-02","arxiv_id":"2112.00971","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hierarchical-reinforcement-learning-based","title":"A Hierarchical Reinforcement Learning Based Optimization Framework for Large-scale Dynamic Pickup and Delivery Problems","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"spatially-and-seamlessly-hierarchical-1","title":"Spatially and Seamlessly Hierarchical Reinforcement Learning for State Space and Policy space in Autonomous Driving","date":"2021-11-10","arxiv_id":"2111.05479","repositories_listed":0,"syntology":null},{"url":null,"slug":"value-function-spaces-skill-centric-state-1","title":"Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning","date":"2021-11-04","arxiv_id":"2111.03189","repositories_listed":0,"syntology":null},{"url":null,"slug":"adjacency-constraint-for-efficient","title":"Adjacency constraint for efficient hierarchical reinforcement learning","date":"2021-10-30","arxiv_id":"2111.00213","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-socialbot-learning-via-multi","title":"Socialbots on Fire: Modeling Adversarial Behaviors of Socialbots via Multi-Agent Hierarchical Reinforcement Learning","date":"2021-10-20","arxiv_id":"2110.10655","repositories_listed":0,"syntology":null},{"url":null,"slug":"provable-hierarchy-based-meta-reinforcement-1","title":"Provable Hierarchy-Based Meta-Reinforcement Learning","date":"2021-10-18","arxiv_id":"2110.09507","repositories_listed":0,"syntology":null},{"url":null,"slug":"wasserstein-unsupervised-reinforcement","title":"Wasserstein Unsupervised Reinforcement Learning","date":"2021-10-15","arxiv_id":"2110.07940","repositories_listed":0,"syntology":null},{"url":null,"slug":"haven-hierarchical-cooperative-multi-agent","title":"HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism","date":"2021-10-14","arxiv_id":"2110.07246","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-when-and-what-to-ask-a-hierarchical-1","title":"A Framework for Learning to Request Rich and Contextually Useful Information from Humans","date":"2021-10-14","arxiv_id":"2110.08258","repositories_listed":0,"syntology":null},{"url":null,"slug":"attaining-interpretability-in-reinforcement","title":"Hierarchical Primitive Composition: Simultaneous Activation of Skills with Inconsistent Action Dimensions in Multiple Hierarchies","date":"2021-10-05","arxiv_id":"2110.01833","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-lane-cruising-using-hierarchical","title":"Multi-lane Cruising Using Hierarchical Planning and Reinforcement Learning","date":"2021-10-01","arxiv_id":"2110.00650","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":"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":"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":"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":"hac-explore-accelerating-exploration-with","title":"HAC Explore: Accelerating Exploration with Hierarchical Reinforcement Learning","date":"2021-08-12","arxiv_id":"2108.05872","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-course-recommendation-system","title":"Adaptive Course Recommendation System","date":"2021-07-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-autonomous-pipeline-inspection-with","title":"Towards Autonomous Pipeline Inspection with Hierarchical Reinforcement Learning","date":"2021-07-08","arxiv_id":"2107.03685","repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-generalizable-skills-via","title":"Discovering Generalizable Skills via Automated Generation of Diverse Tasks","date":"2021-06-26","arxiv_id":"2106.13935","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":"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":"room-clearance-with-feudal-hierarchical","title":"Room Clearance with Feudal Hierarchical Reinforcement Learning","date":"2021-05-24","arxiv_id":"2105.11328","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-for-air","title":"Hierarchical Reinforcement Learning for Air-to-Air Combat","date":"2021-05-03","arxiv_id":"2105.00990","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-framework-1","title":"Hierarchical Reinforcement Learning Framework for Stochastic Spaceflight Campaign Design","date":"2021-03-16","arxiv_id":"2103.08981","repositories_listed":0,"syntology":null},{"url":null,"slug":"potential-impacts-of-smart-homes-on-human","title":"Potential Impacts of Smart Homes on Human Behavior: A Reinforcement Learning Approach","date":"2021-02-26","arxiv_id":"2102.13307","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-logical-options-framework-1","title":"The Logical Options Framework","date":"2021-02-24","arxiv_id":"2102.12571","repositories_listed":0,"syntology":null},{"url":null,"slug":"trader-practical-deep-hierarchical","title":"TradeR: Practical Deep Hierarchical Reinforcement Learning for Trade Execution","date":"2021-02-16","arxiv_id":"2104.00620","repositories_listed":0,"syntology":null},{"url":null,"slug":"stay-alive-with-many-options-a-reinforcement","title":"Learning Skills to Navigate without a Master: A Sequential Multi-Policy Reinforcement Learning Algorithm","date":"2021-01-30","arxiv_id":"2102.00168","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-reinforcement-learning-with-1","title":"Interpretable Reinforcement Learning With Neural Symbolic Logic","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-subgoal-representations-with-slow","title":"Learning Subgoal Representations with Slow Dynamics","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-skill-action-architecture-learning","title":"The Skill-Action Architecture: Learning Abstract Action Embeddings for Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"commission-fee-is-not-enough-a-hierarchical","title":"Deep Stock Trading: A Hierarchical Reinforcement Learning Framework for Portfolio Optimization and Order Execution","date":"2020-12-23","arxiv_id":"2012.12620","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-principles-of-embodied","title":"Hierarchical principles of embodied reinforcement learning: A review","date":"2020-12-18","arxiv_id":"2012.10147","repositories_listed":0,"syntology":null},{"url":null,"slug":"relative-variational-intrinsic-control","title":"Relative Variational Intrinsic Control","date":"2020-12-14","arxiv_id":"2012.07827","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hierarchical-deep-actor-critic-learning","title":"A Hierarchical Deep Actor-Critic Learning Method for Joint Distribution System State Estimation","date":"2020-12-04","arxiv_id":"2012.02880","repositories_listed":0,"syntology":null},{"url":null,"slug":"expanrl-hierarchical-reinforcement-learning","title":"ExpanRL: Hierarchical Reinforcement Learning for Course Concept Expansion in MOOCs","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-efficiency-in-hierarchical-reinforcement","title":"On Efficiency in Hierarchical Reinforcement Learning","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"online-decision-based-visual-tracking-via","title":"Online Decision Based Visual Tracking via Reinforcement Learning","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"from-pixels-to-legs-hierarchical-learning-of","title":"From Pixels to Legs: Hierarchical Learning of Quadruped Locomotion","date":"2020-11-23","arxiv_id":"2011.11722","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-for-3","title":"Hierarchical reinforcement learning for efficient exploration and transfer","date":"2020-11-12","arxiv_id":"2011.06335","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-relay-selection-and-power-allocation","title":"Hierarchical Reinforcement Learning for Relay Selection and Power Optimization in Two-Hop Cooperative Relay Network","date":"2020-11-10","arxiv_id":"2011.04891","repositories_listed":0,"syntology":null},{"url":null,"slug":"behavior-planning-at-urban-intersections","title":"Behavior Planning at Urban Intersections through Hierarchical Reinforcement Learning","date":"2020-11-09","arxiv_id":"2011.04697","repositories_listed":0,"syntology":null},{"url":null,"slug":"nearl-non-explicit-action-reinforcement","title":"NEARL: Non-Explicit Action Reinforcement Learning for Robotic Control","date":"2020-11-02","arxiv_id":"2011.01046","repositories_listed":0,"syntology":null},{"url":null,"slug":"abstract-value-iteration-for-hierarchical","title":"Abstract Value Iteration for Hierarchical Reinforcement Learning","date":"2020-10-29","arxiv_id":"2010.15638","repositories_listed":0,"syntology":null},{"url":null,"slug":"behavior-priors-for-efficient-reinforcement","title":"Behavior Priors for Efficient Reinforcement Learning","date":"2020-10-27","arxiv_id":"2010.14274","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-for-2","title":"Decomposability and Parallel Computation of Multi-Agent LQR","date":"2020-10-16","arxiv_id":"2010.08615","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangling-causal-effects-for-hierarchical","title":"Disentangling causal effects for hierarchical reinforcement learning","date":"2020-10-03","arxiv_id":"2010.01351","repositories_listed":0,"syntology":null},{"url":null,"slug":"relmogen-leveraging-motion-generation-in","title":"ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation","date":"2020-08-18","arxiv_id":"2008.07792","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-model-predictive-and","title":"Comparison of Model Predictive and Reinforcement Learning Methods for Fault Tolerant Control","date":"2020-08-10","arxiv_id":"2008.04403","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchial-reinforcement-learning-in","title":"Hierarchical Reinforcement Learning in StarCraft II with Human Expertise in Subgoals Selection","date":"2020-08-08","arxiv_id":"2008.03444","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-for-deep","title":"Hierarchical Reinforcement Learning for Deep Goal Reasoning: An Expressiveness Analysis","date":"2020-06-21","arxiv_id":"2006.11704","repositories_listed":0,"syntology":null},{"url":null,"slug":"50-years-since-the-marr-ito-and-albus-models","title":"50 years since the Marr, Ito, and Albus models of the cerebellum","date":"2020-06-15","arxiv_id":"2003.05647","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-for-5","title":"Hierarchical reinforcement learning for efficent exploration and transfer","date":"2020-06-12","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"feudal-steering-hierarchical-learning-for","title":"Feudal Steering: Hierarchical Learning for Steering Angle Prediction","date":"2020-06-11","arxiv_id":"2006.06869","repositories_listed":0,"syntology":null},{"url":null,"slug":"gochat-goal-oriented-chatbots-with","title":"GoChat: Goal-oriented Chatbots with Hierarchical Reinforcement Learning","date":"2020-05-24","arxiv_id":"2005.11729","repositories_listed":0,"syntology":null},{"url":null,"slug":"tag-type-auxiliary-guiding-for-code-comment","title":"TAG : Type Auxiliary Guiding for Code Comment Generation","date":"2020-05-06","arxiv_id":"2005.02835","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-ordinary-differential-equation-value","title":"Neural Ordinary Differential Equation Value Networks for Parametrized Action Spaces","date":"2020-02-26","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-functionally-decomposed-hierarchies-1","title":"Learning Functionally Decomposed Hierarchies for Continuous Control Tasks with Path Planning","date":"2020-02-14","arxiv_id":"2002.05954","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-adaptive-hierarchical-reinforcement","title":"Temporal-adaptive Hierarchical Reinforcement Learning","date":"2020-02-06","arxiv_id":"2002.02080","repositories_listed":0,"syntology":null},{"url":null,"slug":"parameter-sharing-in-coagent-networks","title":"Coagent Networks Revisited","date":"2020-01-28","arxiv_id":"2001.10474","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-video-summarization-by","title":"Weakly Supervised Video Summarization by Hierarchical Reinforcement Learning","date":"2020-01-12","arxiv_id":"2001.05864","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-as-a","title":"Hierarchical Reinforcement Learning as a Model of Human Task Interleaving","date":"2020-01-04","arxiv_id":"2001.02122","repositories_listed":0,"syntology":null}],"record_sha256":"31c56ab990a64583027592c3ba253c126dca6623ad86decc093ce8387d0b3d44","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}