Research map / Label-efficient and robust learning / Recognition and long-tail
Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning
Kibeom Kim, Min Whoo Lee, Yoonsung Kim, JeHwan Ryu, Minsu Lee, Byoung-Tak Zhang
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 GACE goal-state classification loss | A3C · V3 | success ratio: 33.45 ± 4.72 -> 52.58 ± 4.09 | Improved |
| Add GDAN attention using the goal-discriminator query (ablation) | A3C+GACE · V3 | success ratio: 52.6% -> 78.2% | Improved |
| Add GACE goal-state classification loss | SAC · R2 Unseen | success ratio: 53.4 ± 6.9 -> 63.0 ± 9.0 | Improved |
| Add GDAN attention using the goal-discriminator query (ablation) | SAC+GACE · R2 Unseen | success ratio: 63.0 ± 9.0 -> 73.3 ± 5.8 | Improved |
| Add GACE goal-state classification loss | SAC · R1 sample efficiency at 63.1% success | SEI (%): 485.41 | Improved |
| Add GDAN attention to GACE (ablation) | SAC+GACE · R1 sample efficiency at 63.1% success | SEI (%): 485.41 -> 398.57 | Hurt |
| Freeze GACE discriminator weights after 10K or 20K updates instead of continuing GACE training (ablation) | A3C+GACE · V1 | learning speed | Hurt |
| Replace GDAN attention with simple concatenation of the state encoding and discriminator query (ablation) | GACE ActorCritic · R1 | success ratio: 81.5 ± 10.0 | Hurt |
| Train separate single-target policies rather than one multi-target policy (ablation) | SAC · R1 | success ratio: 47±11% vs 63.1±6.9% | Hurt |
| Use SAC+CURL instead of SAC on the unseen checkered-background task | SAC · R2 Unseen | success ratio: 53.4 ± 6.9 -> 36.6 ± 3.4 | Hurt |
Closest papers by meaning
- Efficient Multi-task Reinforcement Learning with Cross-Task Policy Guidance (NeurIPS 2024 · similarity 0.86)
- Improving the Continuity of Goal-Achievement Ability via Policy Self-Regularization for Goal-Conditioned Reinforcement Learning (ICML 2025 · similarity 0.86)
- Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning (ICML 2025 · similarity 0.85)
- GOALNET: Interleaving Neural Goal Predicate Inference with Classical Planning for Generalization in Robot Instruction Following (AAAI 2024 · similarity 0.85)
- Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization (NeurIPS 2026 · similarity 0.85)
- $\textit{Hyper-GoalNet}$: Goal-Conditioned Manipulation Policy Learning with HyperNetworks (NeurIPS 2025 · similarity 0.85)
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.
