Research map / Reinforcement learning / Policy gradient and actor-critic
Reachability Constrained Reinforcement Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use reachability constraints and a learned safety value function instead of discounted cumulative-cost constraints | RCRL vs. CRL baselines · safe-control-gym quadrotor trajectory tracking | constraint violation rate | Helped |
| Use reachability constraints and a learned safety value function instead of discounted cumulative-cost constraints | RCRL vs. CRL baselines · Safety-Gym tasks | constraint violation rate | Helped |
| Learn feasible sets through reachability analysis rather than energy-based constraints | RCRL vs. CBF and SI baselines · Safety-Gym tasks | return | Helped |
| Learn the feasible set with reachability analysis rather than CBF constraints | RCRL and MPC-CBF · Double Integrator | feasible set accuracy | Helped |
| Use RCRL to estimate the feasible set | RCRL · Double Integrator | feasible set accuracy | Helped |
| Use a single policy that jointly optimizes reward and persistent safety rather than switching between an optimal policy and a backup safe policy | RCRL · safe-control-gym quadrotor trajectory tracking | return | Helped |
| Use conservative CBF constraints | SAC-CBF · safe-control-gym quadrotor trajectory tracking | return | Hurt |
| Use the paper's empirical SI constraints | SAC-SI · safe-control-gym quadrotor trajectory tracking | constraint violation rate | Hurt |
| Optimize reward using discounted cumulative-cost constraints | SAC-Lagrangian and SAC-Reward Shaping · safe-control-gym quadrotor trajectory tracking | constraint violation rate | Hurt |
| Use energy-based CBF or SI constraints | PPO-CBF and PPO-SI · Safety-Gym tasks | constraint violation rate | Hurt |
| Explore the boundary of the feasible set instead of staying conservatively inside it | RCRL · Training | constraint violation rate | Hurt |
Closest papers by meaning
- Iterative Reachability Estimation for Safe Reinforcement Learning (NeurIPS 2023 · similarity 0.92)
- Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments (ICML 2023 · similarity 0.89)
- Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration (AAAI 2024 · similarity 0.89)
- Feasibility Consistent Representation Learning for Safe Reinforcement Learning (ICML 2024 · similarity 0.88)
- Long-Term Safe Reinforcement Learning with Binary Feedback (AAAI 2024 · similarity 0.88)
- Sampling-Based Safe Reinforcement Learning (NeurIPS 2026 · similarity 0.88)
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.