Hindsight Relabeling is All You Need for Reach-Avoid Learning
cs.LG, cs.AI, q-bio.QM
Submitted: 2025-05-25
Updated: 2026-11-03
Code: https://github.com/katsura-jp/pytorch-cosine-annealing-with-warmup
Terminology
Sources
- Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy
- Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills
- Decision Transformer: Reinforcement Learning via Sequence Modeling
- Contrastive Learning as Goal-Conditioned Reinforcement Learning
- Learning to Reach Goals via Iterated Supervised Learning
- Online Decision Transformer
- Tune: A Research Platform for Distributed Model Selection and Training
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis