Research map / Reinforcement learning / Visual and representation RL
Adversarial Actor-Critic Method for Task and Motion Planning Problems Using Planning Experience
Beomjoon Kim, Leslie Pack Kaelbling, Tomás Lozano-Pérez
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 |
|---|---|---|---|
| guide planner with ADMON-learned policy instead of uniform sampling | sampling-based G-TAMP planner · Conveyor belt domain | planning time to 95% optimal: 1200+ s -> 400 s | Improved |
| guide planner with ADMON-learned policy instead of uniform sampling | sampling-based G-TAMP planner · Object fetch domain | planning time to clear optimal objects: 3500 s -> 1500 s | Improved |
| ADMON (reward + imitation of planning data) vs PPO/DDPG | policy learning · Conveyor belt domain | reward learning curve vs data size | Improved |
| ADMON vs GAIL (treating planning data as optimal demos) | policy learning · Conveyor belt domain | reward learning curve | Improved |
| ADMON vs GAIL | policy learning · Object fetch domain | reward learning curve | Improved |
| ADMON vs DDPG | policy learning · Object fetch domain | reward learning curve | Improved |
| ADMON vs DDPG in planning | policy-guided planner · Object fetch domain | objects cleared over time | Improved |
| PPO vs ADMON in object fetch with more transitions | PPO · Object fetch domain | reward learning curve | Mixed |
Closest papers by meaning
- Model-Augmented Actor-Critic: Backpropagating through Paths (ICLR 2020 · similarity 0.88)
- Guiding Search in Continuous State-Action Spaces by Learning an Action Sampler From Off-Target Search Experience (AAAI 2018 · similarity 0.88)
- Discovering State and Action Abstractions for Generalized Task and Motion Planning (AAAI 2022 · similarity 0.87)
- Towards Improvisational TAMP: Learning Low-Level Shortcuts in Abstract Planning Graphs (ICLR 2026 · similarity 0.87)
- Offline Actor-Critic Reinforcement Learning Scales to Large Models (ICML 2024 · similarity 0.86)
- Efficient Robotic Policy Learning via Latent Space Backward Planning (ICML 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.
