arXiv Machine Learning
Recursive Value Learning for Long-Horizon Offline Goal-Conditioned RL
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
3d ago
PathBridger: Subgoal Bridges for Offline Goal-Conditioned Reinforcement Learning
arXiv:2608.29061v1 Announce Type: new Abstract: Offline goal-conditioned reinforcement learning (GCRL) aims to learn policies for reaching diverse goals entirely from fixed trajectory data. Long-hori...
arXiv Machine Learning
Jul 24
Offline RL with Hierarchical Action Chunking
arXiv:2607. 20834v1 Announce Type: new Abstract: Offline goal-conditioned reinforcement learning (RL) holds the promise of learning general-purpose policies from static datasets.
Hugging Face Trending Papers
Jul 23
Offline RL with Hierarchical Action Chunking
Offline goal-conditioned reinforcement learning (RL) holds the promise of learning general-purpose policies from static datasets. However, scaling these methods to long-horizon tasks remains a challenge due to the curse of horizon, where value estimation errors can compound through long chains of bootstrapped Bellman backups.
arXiv AI
Jul 20
Process Reward Informed Tree Rollout for Effective Multi-Turn RL
arXiv:2607. 15610v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key approach for training LLM agents, yet popular methods such as GRPO/RLOO rely on multiple independently sampled complete trajectories for advantage estimation.
arXiv Machine Learning
Jun 9
Counterfactual Transport Flows for Offline Conservative Trajectory Refinement
arXiv:2606. 09115v1 Announce Type: new Abstract: Offline reinforcement learning (RL) offers a path to policy improvement from logged data alone, using historical returns or other measurable outcomes as world feedback.
arXiv AI
Jul 23
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
arXiv:2601. 06487v3 Announce Type: replace-cross Abstract: Reinforcement learning has substantially improved the performance of LLM agents on tasks with verifiable outcomes, but it still struggles on open-ended agent tasks with vast solution spaces (e.