JMLR 2023 papers on Reinforcement learning
18 of the 354 papers published in JMLR 2023 (5.1%) are on Reinforcement learning, compared with 3.9% at JMLR 2022. They fall into 5 topics.
See JMLR 2023 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 · 6 papers
- q-Learning in Continuous Time (31 citations)
- Off-Policy Actor-Critic with Emphatic Weightings (2 citations)
- Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learning
- Adaptation Augmented Model-based Policy Optimization
- Convex Reinforcement Learning in Finite Trials
- Single Timescale Actor-Critic Method to Solve the Linear Quadratic Regulator with Convergence Guarantees
MDPs and planning · 5 papers
- Q-Learning for MDPs with General Spaces: Convergence and Near Optimality via Quantization under Weak Continuity (19 citations)
- Jump Interval-Learning for Individualized Decision Making with Continuous Treatments
- Learning Good State and Action Representations for Markov Decision Process via Tensor Decomposition
- Provably Sample-Efficient Model-Free Algorithm for MDPs with Peak Constraints
- Reinforcement Learning for Joint Optimization of Multiple Rewards
