Constrained Variational Policy Optimization for Hybrid Action Spaces
cs.LG
Submitted: 2026-11-09
Updated: 2026-11-09
Comments: 29 pages, 8 figures, 5 tables. This work extends constrained variational policy optimization from continuous-action spaces to hybrid discrete-continuous action spaces
Code: https://github.com/aozhouza/CHPO
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Maximum a Posteriori Policy Optimisation
- Lyapunov-based Safe Policy Optimization for Continuous Control
- Discrete and Continuous Action Representation for Practical RL in Video Games
- Deep Reinforcement Learning in Parameterized Action Space
- Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
- Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis