Research map / Reinforcement learning / Visual and representation RL
C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks
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 |
|---|---|---|---|
| Add training-time waypoint sampling to collect experience | C-Learning · Maze-11x11 | learning progress | Helped |
| Add training-time waypoint sampling to collect experience | C-Learning · 2D navigation mazes | distance to goal | Helped |
| Add training-time waypoint sampling to collect experience | C-Learning · MetaWorld Reach | learning speed | Hurt |
| Add training-time waypoint sampling to collect experience | C-Learning · MetaWorld Push and Push-Wall | performance | Helped |
| Add training-time waypoint sampling to collect experience | C-Learning · Obstacle-Drawer-Close, Obstacle-Drawer-Open, and Push-Two | task performance | Helped |
| Use sampled waypoints to collect new data rather than modify the policy-learning objective (ablation) | C-Planning · Obstacle-Drawer-Close, Obstacle-Drawer-Open, and Push-Two | learning progress | Helped |
| Add test-time SoRB planning (ablation) | C-Planning · C-Planning evaluation tasks | performance | No clear effect |
| Vary the number of waypoint resamples before commanding the final goal (ablation) | C-Planning · C-Planning evaluation tasks | task-solving performance | No clear effect |
| Use the optimal policy's state distribution as the initial state distribution | C-Learning · 2D navigation task | learning speed: 2.4x faster | Helped |
Closest papers by meaning
- Imitating Graph-Based Planning with Goal-Conditioned Policies (ICLR 2023 · similarity 0.90)
- Test-Time Graph Search for Goal-Conditioned Reinforcement Learning (ICML 2026 · similarity 0.90)
- Scaling Goal-conditioned Reinforcement Learning with Multistep Quasimetric Distances (ICLR 2026 · similarity 0.89)
- Diffusion Subgoal Planning for Long-Horizon Offline Goal-Conditioned Reinforcement Learning (NeurIPS 2026 · similarity 0.89)
- Flattening Hierarchies with Policy Bootstrapping (NeurIPS 2025 · similarity 0.88)
- PcLast: Discovering Plannable Continuous Latent States (ICML 2024 · similarity 0.87)
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.