{"total":46,"rows":[{"id":"2306.17100","title":"RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark","created":"2023-06-29","cited_by_count":71,"area":null},{"id":"2109.09717","title":"Generalization in Mean Field Games by Learning Master Policies","created":"2021-09-20","cited_by_count":28,"area":null},{"id":"2205.02388","title":"Interactive Grounded Language Understanding in a Collaborative Environment: IGLU 2021","created":"2022-05-05","cited_by_count":23,"area":null},{"id":"2110.07594","title":"The Neural MMO Platform for Massively Multiagent Research","created":"2021-10-14","cited_by_count":17,"area":null},{"id":"2110.06536","title":"NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment","created":"2021-10-13","cited_by_count":15,"area":null},{"id":"2207.03270","title":"gym-DSSAT: a crop model turned into a Reinforcement Learning environment","created":"2022-07-07","cited_by_count":13,"area":null},{"id":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11,"area":null},{"id":"2112.02852","title":"Target Entropy Annealing for Discrete Soft Actor-Critic","created":"2021-12-06","cited_by_count":10,"area":null},{"id":"2202.11818","title":"Consistent Dropout for Policy Gradient Reinforcement Learning","created":"2022-02-23","cited_by_count":10,"area":null},{"id":"2306.16688","title":"SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2206.10944","title":"POGEMA: Partially Observable Grid Environment for Multiple Agents","created":"2022-06-22","cited_by_count":6,"area":null},{"id":"2405.01409","title":"Goal-conditioned reinforcement learning for ultrasound navigation guidance","created":"2024-05-02","cited_by_count":6,"area":null},{"id":"2111.00963","title":"Machine Learning aided Crop Yield Optimization","created":"2021-11-01","cited_by_count":5,"area":null},{"id":"2502.08681","title":"Centrally Coordinated Multi-Agent Reinforcement Learning for Power Grid Topology Control","created":"2025-02-12","cited_by_count":5,"area":null},{"id":"2107.09996","title":"MarsExplorer: Exploration of Unknown Terrains via Deep Reinforcement Learning and Procedurally Generated Environments","created":"2021-07-21","cited_by_count":4,"area":null},{"id":"2302.14188","title":"Exposure-Based Multi-Agent Inspection of a Tumbling Target Using Deep Reinforcement Learning","created":"2023-02-27","cited_by_count":4,"area":null},{"id":"2309.08477","title":"Deep Multi-Agent Reinforcement Learning for Decentralized Active Hypothesis Testing","created":"2023-09-14","cited_by_count":4,"area":null},{"id":"2102.02304","title":"Improved Cooperation by Exploiting a Common Signal","created":"2021-02-03","cited_by_count":3,"area":null},{"id":"2106.06060","title":"AI-driven Prices for Externalities and Sustainability in Production Markets","created":"2021-06-10","cited_by_count":3,"area":null},{"id":"2106.11345","title":"Cogment: Open Source Framework For Distributed Multi-actor Training, Deployment & Operations","created":"2021-06-21","cited_by_count":3,"area":null},{"id":"2306.13587","title":"Creating Valid Adversarial Examples of Malware","created":"2023-06-23","cited_by_count":3,"area":null},{"id":"2312.04030","title":"Modeling Boundedly Rational Agents with Latent Inference Budgets","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2109.14711","title":"Explanation-Aware Experience Replay in Rule-Dense Environments","created":"2021-09-29","cited_by_count":2,"area":null},{"id":"2110.01101","title":"Parallel Actors and Learners: A Framework for Generating Scalable RL Implementations","created":"2021-10-03","cited_by_count":2,"area":null},{"id":"2110.08124","title":"Decentralized Cooperative Lane Changing at Freeway Weaving Areas Using Multi-Agent Deep Reinforcement Learning","created":"2021-10-05","cited_by_count":2,"area":null},{"id":"2207.07710","title":"Outcome-Guided Counterfactuals for Reinforcement Learning Agents from a Jointly Trained Generative Latent Space","created":"2022-07-15","cited_by_count":2,"area":null},{"id":"2302.07337","title":"Graph Attention Multi-Agent Fleet Autonomy for Advanced Air Mobility","created":"2023-02-14","cited_by_count":2,"area":null},{"id":"2310.03915","title":"Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2106.02412","title":"Resource Allocation in Disaggregated Data Centre Systems with Reinforcement Learning","created":"2021-06-04","cited_by_count":1,"area":null},{"id":"2108.10533","title":"Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning","created":"2021-08-24","cited_by_count":1,"area":null},{"id":"2209.02562","title":"Project proposal: A modular reinforcement learning based automated theorem prover","created":"2022-09-06","cited_by_count":1,"area":null},{"id":"2304.04911","title":"Real-Time Model-Free Deep Reinforcement Learning for Force Control of a Series Elastic Actuator","created":"2023-04-11","cited_by_count":1,"area":null},{"id":"2309.09881","title":"Deep Reinforcement Learning for the Joint Control of Traffic Light Signaling and Vehicle Speed Advice","created":"2023-09-18","cited_by_count":1,"area":null},{"id":"2412.00534","title":"Towards Fault Tolerance in Multi-Agent Reinforcement Learning","created":"2024-11-30","cited_by_count":1,"area":null},{"id":"2109.09597","title":"Two Approaches to Building Collaborative, Task-Oriented Dialog Agents through Self-Play","created":"2021-09-20","cited_by_count":0,"area":null},{"id":"2202.13436","title":"Neural-Progressive Hedging: Enforcing Constraints in Reinforcement Learning with Stochastic Programming","created":"2022-02-27","cited_by_count":0,"area":null},{"id":"2204.04892","title":"JORLDY: a fully customizable open source framework for reinforcement learning","created":"2022-04-11","cited_by_count":0,"area":null},{"id":"2205.07973","title":"Many Field Packet Classification with Decomposition and Reinforcement Learning","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2207.03945","title":"High Performance Simulation for Scalable Multi-Agent Reinforcement Learning","created":"2022-07-08","cited_by_count":0,"area":null},{"id":"2210.08003","title":"Hierarchical Decentralized Deep Reinforcement Learning Architecture for a Simulated Four-Legged Agent","created":"2022-09-21","cited_by_count":0,"area":null},{"id":"2210.13906","title":"One-shot, Offline and Production-Scalable PID Optimisation with Deep Reinforcement Learning","created":"2022-10-25","cited_by_count":0,"area":null},{"id":"2211.02466","title":"Network Aware Compute and Memory Allocation in Optically Composable Data Centres with Deep Reinforcement Learning and Graph Neural Networks","created":"2022-10-26","cited_by_count":0,"area":null},{"id":"2302.12403","title":"Plume: A Framework for High Performance Deep RL Network Controllers via Prioritized Trace Sampling","created":"2023-02-24","cited_by_count":0,"area":null},{"id":"2303.00004","title":"Parameter Optimization of LLC-Converter with multiple operation points using Reinforcement Learning","created":"2023-02-28","cited_by_count":0,"area":null},{"id":"2303.04944","title":"On the Benefits of Biophysical Synapses","created":"2023-03-08","cited_by_count":0,"area":null},{"id":"2608.12363","title":"EU-ETS under attack? The impact of carbon price suppression on the decarbonization of the power sector","created":"2026-07-06","cited_by_count":0,"area":null}],"next_cursor":null}