{"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/128","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":128,"pages_in_order":132,"rows_per_page":100,"rows":[12701,12800],"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/127","next":"/task/reinforcement-learning/papers/129","papers":[{"url":null,"slug":"reinforcement-learning-with-temporal-logic","title":"Reinforcement Learning With Temporal Logic Rewards","date":"2016-12-11","arxiv_id":"1612.03471","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-deep-learning-with-spiking-neurons-in","title":"Towards deep learning with spiking neurons in energy based models with contrastive Hebbian plasticity","date":"2016-12-09","arxiv_id":"1612.03214","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchy-through-composition-with-linearly","title":"Hierarchy through Composition with Linearly Solvable Markov Decision Processes","date":"2016-12-08","arxiv_id":"1612.02757","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-primal-dual-methods-and-sample","title":"Stochastic Primal-Dual Methods and Sample Complexity of Reinforcement Learning","date":"2016-12-08","arxiv_id":"1612.02516","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-information-seeking-agents","title":"Towards Information-Seeking Agents","date":"2016-12-08","arxiv_id":"1612.02605","repositories_listed":0,"syntology":null},{"url":null,"slug":"transition-based-versus-state-based-reward","title":"Transition-based versus State-based Reward Functions for MDPs with Value-at-Risk","date":"2016-12-07","arxiv_id":"1612.02088","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-of-robotic-tasks-without-a","title":"Deep Learning of Robotic Tasks without a Simulator using Strong and Weak Human Supervision","date":"2016-12-04","arxiv_id":"1612.01086","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-superoptimize-programs-workshop","title":"Learning to superoptimize programs - Workshop Version","date":"2016-12-04","arxiv_id":"1612.01094","repositories_listed":0,"syntology":null},{"url":null,"slug":"success-probability-of-exploration-a-concrete","title":"Success Probability of Exploration: a Concrete Analysis of Learning Efficiency","date":"2016-12-02","arxiv_id":"1612.00882","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-optimal-training-of-animal-behavior","title":"Adaptive optimal training of animal behavior","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapping-incremental-dialogue-systems","title":"Bootstrapping incremental dialogue systems: using linguistic knowledge to learn from minimal data","date":"2016-12-01","arxiv_id":"1612.00347","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizing-skills-with-semi-supervised","title":"Generalizing Skills with Semi-Supervised Reinforcement Learning","date":"2016-12-01","arxiv_id":"1612.00429","repositories_listed":0,"syntology":null},{"url":null,"slug":"guided-policy-search-via-approximate-mirror","title":"Guided Policy Search via Approximate Mirror Descent","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"linear-feature-encoding-for-reinforcement","title":"Linear Feature Encoding for Reinforcement Learning","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"showing-versus-doing-teaching-by","title":"Showing versus doing: Teaching by demonstration","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-for-multi-task-reinforcement","title":"Exploration for Multi-task Reinforcement Learning with Deep Generative Models","date":"2016-11-29","arxiv_id":"1611.09894","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-policy-gradient-by-exploring-under","title":"Improving Policy Gradient by Exploring Under-appreciated Rewards","date":"2016-11-28","arxiv_id":"1611.09321","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-compose-words-into-sentences-with","title":"Learning to Compose Words into Sentences with Reinforcement Learning","date":"2016-11-28","arxiv_id":"1611.09100","repositories_listed":0,"syntology":null},{"url":null,"slug":"nonparametric-general-reinforcement-learning","title":"Nonparametric General Reinforcement Learning","date":"2016-11-28","arxiv_id":"1611.08944","repositories_listed":0,"syntology":null},{"url":null,"slug":"handwriting-profiling-using-generative","title":"Handwriting Profiling using Generative Adversarial Networks","date":"2016-11-27","arxiv_id":"1611.08789","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiscale-inverse-reinforcement-learning","title":"Multiscale Inverse Reinforcement Learning using Diffusion Wavelets","date":"2016-11-24","arxiv_id":"1611.08070","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-co-robots-learn-to-teach","title":"Can Co-robots Learn to Teach?","date":"2016-11-22","arxiv_id":"1611.07490","repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-attention-models-for-depth-based","title":"Recurrent Attention Models for Depth-Based Person Identification","date":"2016-11-22","arxiv_id":"1611.07212","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-learning-approach-for-joint-video","title":"A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games","date":"2016-11-21","arxiv_id":"1611.07078","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-lens-how-much-memory-does-an-agent-use","title":"Memory Lens: How Much Memory Does an Agent Use?","date":"2016-11-21","arxiv_id":"1611.06928","repositories_listed":0,"syntology":null},{"url":null,"slug":"options-discovery-with-budgeted-reinforcement","title":"Options Discovery with Budgeted Reinforcement Learning","date":"2016-11-21","arxiv_id":"1611.06824","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-in-rich-observation","title":"Reinforcement Learning in Rich-Observation MDPs using Spectral Methods","date":"2016-11-11","arxiv_id":"1611.03907","repositories_listed":0,"syntology":null},{"url":null,"slug":"estimating-dynamic-treatment-regimes-in","title":"Estimating Dynamic Treatment Regimes in Mobile Health Using V-learning","date":"2016-11-10","arxiv_id":"1611.03531","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairness-in-reinforcement-learning","title":"Fairness in Reinforcement Learning","date":"2016-11-09","arxiv_id":"1611.03071","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-tutor-conservative-fine-tuning-of","title":"Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control","date":"2016-11-09","arxiv_id":"1611.02796","repositories_listed":0,"syntology":null},{"url":null,"slug":"averaged-dqn-variance-reduction-and","title":"Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning","date":"2016-11-07","arxiv_id":"1611.01929","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-approach-for","title":"Reinforcement Learning Approach for Parallelization in Filters Aggregation Based Feature Selection Algorithms","date":"2016-11-07","arxiv_id":"1611.02047","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-question-answering-for-long","title":"Hierarchical Question Answering for Long Documents","date":"2016-11-06","arxiv_id":"1611.01839","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-perform-physics-experiments-via","title":"Learning to Perform Physics Experiments via Deep Reinforcement Learning","date":"2016-11-06","arxiv_id":"1611.01843","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-differentiable-physics-engine-for-deep","title":"A Differentiable Physics Engine for Deep Learning in Robotics","date":"2016-11-05","arxiv_id":"1611.01652","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-policy-gradient-and-q-learning","title":"Combining policy gradient and Q-learning","date":"2016-11-05","arxiv_id":"1611.01626","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-learning-with-deep-model-based","title":"Multi-task learning with deep model based reinforcement learning","date":"2016-11-04","arxiv_id":"1611.01457","repositories_listed":0,"syntology":null},{"url":null,"slug":"combating-reinforcement-learnings-sisyphean","title":"Combating Reinforcement Learning's Sisyphean Curse with Intrinsic Fear","date":"2016-11-03","arxiv_id":"1611.01211","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-locomotion-skills-using-deeprl-does","title":"Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?","date":"2016-11-03","arxiv_id":"1611.01055","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantile-reinforcement-learning","title":"Quantile Reinforcement Learning","date":"2016-11-03","arxiv_id":"1611.00862","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-a-deep-reinforcement-learning-agent-for","title":"Using a Deep Reinforcement Learning Agent for Traffic Signal Control","date":"2016-11-03","arxiv_id":"1611.01142","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-runtime-parameters-in-computer","title":"Learning Runtime Parameters in Computer Systems with Delayed Experience Injection","date":"2016-10-31","arxiv_id":"1610.09903","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-decision-processes-with-low","title":"Contextual Decision Processes with Low Bellman Rank are PAC-Learnable","date":"2016-10-29","arxiv_id":"1610.09512","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-enhanced-machine-learning","title":"Quantum-enhanced machine learning","date":"2016-10-26","arxiv_id":"1610.08251","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-in-conflicting","title":"Reinforcement Learning in Conflicting Environments for Autonomous Vehicles","date":"2016-10-22","arxiv_id":"1610.07089","repositories_listed":0,"syntology":null},{"url":null,"slug":"modular-deep-q-networks-for-sim-to-real","title":"Modular Deep Q Networks for Sim-to-real Transfer of Visuo-motor Policies","date":"2016-10-21","arxiv_id":"1610.06781","repositories_listed":0,"syntology":null},{"url":null,"slug":"utilization-of-deep-reinforcement-learning","title":"Utilization of Deep Reinforcement Learning for saccadic-based object visual search","date":"2016-10-20","arxiv_id":"1610.06492","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-approach-to-the-view","title":"A Reinforcement Learning Approach to the View Planning Problem","date":"2016-10-19","arxiv_id":"1610.06204","repositories_listed":0,"syntology":null},{"url":null,"slug":"particle-swarm-optimization-for-generating","title":"Particle Swarm Optimization for Generating Interpretable Fuzzy Reinforcement Learning Policies","date":"2016-10-19","arxiv_id":"1610.05984","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-contrastive-divergence-with-generative","title":"Online Contrastive Divergence with Generative Replay: Experience Replay without Storing Data","date":"2016-10-18","arxiv_id":"1610.05555","repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-3d-attentional-networks-for-end-to","title":"Recurrent 3D Attentional Networks for End-to-End Active Object Recognition","date":"2016-10-14","arxiv_id":"1610.04308","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-end-of-optimism-an-asymptotic-analysis-of","title":"The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits","date":"2016-10-14","arxiv_id":"1610.04491","repositories_listed":0,"syntology":null},{"url":null,"slug":"sim-to-real-robot-learning-from-pixels-with","title":"Sim-to-Real Robot Learning from Pixels with Progressive Nets","date":"2016-10-13","arxiv_id":"1610.04286","repositories_listed":0,"syntology":null},{"url":null,"slug":"introduction-to-the-industrial-benchmark","title":"Introduction to the \"Industrial Benchmark\"","date":"2016-10-12","arxiv_id":"1610.03793","repositories_listed":0,"syntology":null},{"url":null,"slug":"navigational-instruction-generation-as","title":"Navigational Instruction Generation as Inverse Reinforcement Learning with Neural Machine Translation","date":"2016-10-11","arxiv_id":"1610.03164","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-multi-agent-reinforcement-learning-for","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","date":"2016-10-11","arxiv_id":"1610.03295","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-from-simulation-to-real-world","title":"Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model","date":"2016-10-11","arxiv_id":"1610.03518","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalizing-a-dialogue-system-with-transfer","title":"Personalizing a Dialogue System with Transfer Reinforcement Learning","date":"2016-10-10","arxiv_id":"1610.02891","repositories_listed":0,"syntology":null},{"url":null,"slug":"situational-awareness-by-risk-conscious","title":"Situational Awareness by Risk-Conscious Skills","date":"2016-10-10","arxiv_id":"1610.02847","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-from-raw-pixels","title":"Deep Reinforcement Learning From Raw Pixels in Doom","date":"2016-10-07","arxiv_id":"1610.02164","repositories_listed":0,"syntology":null},{"url":null,"slug":"connecting-generative-adversarial-networks","title":"Connecting Generative Adversarial Networks and Actor-Critic Methods","date":"2016-10-06","arxiv_id":"1610.01945","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-cognitive-exploration-through-deep","title":"Towards Cognitive Exploration through Deep Reinforcement Learning for Mobile Robots","date":"2016-10-06","arxiv_id":"1610.01733","repositories_listed":0,"syntology":null},{"url":null,"slug":"epopt-learning-robust-neural-network-policies","title":"EPOpt: Learning Robust Neural Network Policies Using Model Ensembles","date":"2016-10-05","arxiv_id":"1610.01283","repositories_listed":0,"syntology":null},{"url":null,"slug":"reset-free-guided-policy-search-efficient","title":"Reset-Free Guided Policy Search: Efficient Deep Reinforcement Learning with Stochastic Initial States","date":"2016-10-04","arxiv_id":"1610.01112","repositories_listed":0,"syntology":null},{"url":null,"slug":"collective-robot-reinforcement-learning-with","title":"Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search","date":"2016-10-03","arxiv_id":"1610.00673","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-robotic","title":"Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates","date":"2016-10-03","arxiv_id":"1610.00633","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-tensegrity","title":"Deep Reinforcement Learning for Tensegrity Robot Locomotion","date":"2016-09-28","arxiv_id":"1609.09049","repositories_listed":0,"syntology":null},{"url":null,"slug":"ubuntuworld-10-lts-a-platform-for-automated","title":"UbuntuWorld 1.0 LTS - A Platform for Automated Problem Solving & Troubleshooting in the Ubuntu OS","date":"2016-09-27","arxiv_id":"1609.08524","repositories_listed":0,"syntology":null},{"url":null,"slug":"regulating-reward-training-by-means-of","title":"Regulating Reward Training by Means of Certainty Prediction in a Neural Network-Implemented Pong Game","date":"2016-09-23","arxiv_id":"1609.07434","repositories_listed":0,"syntology":null},{"url":null,"slug":"exact-sampling-from-determinantal-point","title":"Exact Sampling from Determinantal Point Processes","date":"2016-09-22","arxiv_id":"1609.06840","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-modular-neural-network-policies-for","title":"Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer","date":"2016-09-22","arxiv_id":"1609.07088","repositories_listed":0,"syntology":null},{"url":null,"slug":"modelling-stock-market-investors-as","title":"Modelling Stock-market Investors as Reinforcement Learning Agents [Correction]","date":"2016-09-20","arxiv_id":"1609.06086","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-deep-symbolic-reinforcement-learning","title":"Towards Deep Symbolic Reinforcement Learning","date":"2016-09-18","arxiv_id":"1609.05518","repositories_listed":0,"syntology":null},{"url":"/paper/reasonet-learning-to-stop-reading-in-machine","slug":"reasonet-learning-to-stop-reading-in-machine","title":"ReasoNet: Learning to Stop Reading in Machine Comprehension","date":"2016-09-17","arxiv_id":"1609.05284","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-potential","title":"Exploration Potential","date":"2016-09-16","arxiv_id":"1609.04994","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-spoken-content-retrieval-by-deep","title":"Interactive Spoken Content Retrieval by Deep Reinforcement Learning","date":"2016-09-16","arxiv_id":"1609.05234","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-reinforcement-learning-a-survey","title":"Bayesian Reinforcement Learning: A Survey","date":"2016-09-14","arxiv_id":"1609.04436","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-simulation-for-robot-arm-control-with-deep","title":"3D Simulation for Robot Arm Control with Deep Q-Learning","date":"2016-09-13","arxiv_id":"1609.03759","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-centralized-reinforcement-learning-method","title":"A centralized reinforcement learning method for multi-agent job scheduling in Grid","date":"2016-09-11","arxiv_id":"1609.03157","repositories_listed":0,"syntology":null},{"url":null,"slug":"episodic-exploration-for-deep-deterministic","title":"Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks","date":"2016-09-10","arxiv_id":"1609.02993","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialogue-manager-domain-adaptation-using","title":"Dialogue manager domain adaptation using Gaussian process reinforcement learning","date":"2016-09-09","arxiv_id":"1609.02846","repositories_listed":0,"syntology":null},{"url":null,"slug":"unifying-task-specification-in-reinforcement","title":"Unifying task specification in reinforcement learning","date":"2016-09-07","arxiv_id":"1609.01995","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-photon-in-hierarchical-architecture","title":"Single photon in hierarchical architecture for physical reinforcement learning: Photon intelligence","date":"2016-09-01","arxiv_id":"1609.00686","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-probabilistic-trajectory","title":"Adaptive Probabilistic Trajectory Optimization via Efficient Approximate Inference","date":"2016-08-22","arxiv_id":"1608.06235","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-human-reading-with-neural-attention","title":"Modeling Human Reading with Neural Attention","date":"2016-08-19","arxiv_id":"1608.05604","repositories_listed":0,"syntology":null},{"url":null,"slug":"bbq-networks-efficient-exploration-in-deep-1","title":"BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems","date":"2016-08-17","arxiv_id":"1608.05081","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-problem-approximate-planning-of-pomdps","title":"Open Problem: Approximate Planning of POMDPs in the class of Memoryless Policies","date":"2016-08-17","arxiv_id":"1608.04996","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-algorithms-for-regret","title":"Reinforcement Learning algorithms for regret minimization in structured Markov Decision Processes","date":"2016-08-17","arxiv_id":"1608.04929","repositories_listed":0,"syntology":null},{"url":null,"slug":"density-matching-reward-learning","title":"Density Matching Reward Learning","date":"2016-08-12","arxiv_id":"1608.03694","repositories_listed":0,"syntology":null},{"url":null,"slug":"perceptual-reward-functions","title":"Perceptual Reward Functions","date":"2016-08-12","arxiv_id":"1608.03824","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuroevolution-based-inverse-reinforcement","title":"Neuroevolution-Based Inverse Reinforcement Learning","date":"2016-08-09","arxiv_id":"1608.02971","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-lower-bounds-for-regret-in-reinforcement","title":"On Lower Bounds for Regret in Reinforcement Learning","date":"2016-08-09","arxiv_id":"1608.02732","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-adaptation-of-deep-architectures-with","title":"Online Adaptation of Deep Architectures with Reinforcement Learning","date":"2016-08-08","arxiv_id":"1608.02292","repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-latent-states-for-model-learning","title":"Discovering Latent States for Model Learning: Applying Sensorimotor Contingencies Theory and Predictive Processing to Model Context","date":"2016-08-01","arxiv_id":"1608.00359","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-sensorimotor-reinforcement-learning","title":"A Sensorimotor Reinforcement Learning Framework for Physical Human-Robot Interaction","date":"2016-07-27","arxiv_id":"1607.07939","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-stochastic-composition","title":"Accelerating Stochastic Composition Optimization","date":"2016-07-25","arxiv_id":"1607.07329","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-conditional-distributions-via","title":"Learning from Conditional Distributions via Dual Embeddings","date":"2016-07-15","arxiv_id":"1607.04579","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequential-cost-sensitive-feature-acquisition","title":"Sequential Cost-Sensitive Feature Acquisition","date":"2016-07-13","arxiv_id":"1607.03691","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-bridge-bidding-using-deep","title":"Automatic Bridge Bidding Using Deep Reinforcement Learning","date":"2016-07-12","arxiv_id":"1607.03290","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-is-posterior-sampling-better-than","title":"Why is Posterior Sampling Better than Optimism for Reinforcement Learning?","date":"2016-07-01","arxiv_id":"1607.00215","repositories_listed":0,"syntology":null}],"record_sha256":"33f9cbbe05e784b5a36403331bc1c220b5b2721a9e779190afc90ff20098474a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}