Autonomous Learning From Success and Failure: Goal-Conditioned Supervised Learning with Negative Feedback
cs.LG, cs.AI
Submitted: 2025-09-03
Updated: 2026-11-15
Code: https://github.com/zeqiang-zhang/gcsl_nf
Terminology
Sources
- Maximum a Posteriori Policy Optimisation
- Big Self-Supervised Models are Strong Semi-Supervised Learners
- InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training
- Explaining Online Reinforcement Learning Decisions of Self-Adaptive Systems
- Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning
- Independent Generative Adversarial Self-Imitation Learning in Cooperative Multiagent Systems
- Deep Successor Reinforcement Learning
- Continuous control with deep reinforcement learning
- Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
- Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
- Hindsight policy gradients
- Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
- Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards
- Self-supervised Learning of Distance Functions for Goal-Conditioned Reinforcement Learning
- Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL
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