Research map / Reinforcement learning / Policy gradient and actor-critic
Hamilton-Jacobi Deep Q-Learning for Deterministic Continuous-Time Systems with Lipschitz Continuous Controls
Jeongho Kim, Jaeuk Shin, Insoon Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add double Q-learning style action selection with target network (ablation) | HJ DQN · Swimmer-v2 | final average return | Improved |
| vary sampling interval h from 0.01 to 0.08 (then to 0.16) (ablation) | HJ DQN · Swimmer-v2 | final performance and learning speed: best at h = 0.08 | Mixed |
| increase control Lipschitz constant L from 1 to 10 or more (ablation) | HJ DQN · Swimmer-v2 | final reward: L = 1 lowest; L >= 10 similar; slight decrease for L from 20 to 40 | Improved |
| add tanh smoothing to action update (ablation) | HJ DQN · 20-dimensional LQ problem | action oscillation | Improved |
| replace DDPG actor network with HJ DQN optimal control ODE | DDPG · MuJoCo Hopper, Swimmer, HalfCheetah, Walker2d | return | Mixed |
| use HJ DQN instead of DDPG | DDPG · LQ problem (d=20) | log cost ratio to optimal | Improved |
Closest papers by meaning
- Universal Approximation Theorem of Deep Q-Networks (ICML 2025 · similarity 0.89)
- Deep learning for continuous-time stochastic control with jumps (NeurIPS 2025 · similarity 0.88)
- Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network (ICML 2025 · similarity 0.87)
- A Temporal Difference Method for Stochastic Continuous Dynamics (NeurIPS 2025 · similarity 0.86)
- Actor-Free Continuous Control via Structurally Maximizable Q-Functions (NeurIPS 2025 · similarity 0.86)
- Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
