JMLR 2024 papers on Reinforcement learning
16 of the 391 papers published in JMLR 2024 (4.1%) are on Reinforcement learning, compared with 5.1% at JMLR 2023. They fall into 5 topics.
See JMLR 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Policy gradient and actor-critic · 5 papers
- Policy Gradient Methods in the Presence of Symmetries and State Abstractions (3 citations)
- Sample Complexity of Neural Policy Mirror Descent for Policy Optimization on Low-Dimensional Manifolds (1 citation)
- Matryoshka Policy Gradient for Entropy-Regularized RL: Convergence and Global Optimality
- Rethinking Discount Regularization: New Interpretations, Unintended Consequences, and Solutions for Regularization in Reinforcement Learning
- A New, Physics-Informed Continuous-Time Reinforcement Learning Algorithm with Performance Guarantees
MDPs and planning · 4 papers
- Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity (51 citations)
- Sample Complexity of Variance-Reduced Distributionally Robust Q-Learning (13 citations)
- Model-Free Representation Learning and Exploration in Low-Rank MDPs
- On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control
Visual and representation RL · 4 papers
- OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research (63 citations)
- QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration (25 citations)
- Pearl: A Production-Ready Reinforcement Learning Agent (7 citations)
- RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control (7 citations)
Offline RL · 2 papers
Imitation learning · 1 paper
- Sample-efficient Adversarial Imitation Learning (2 citations)
