No article text was recorded for this version.
online reward adaptation
Version 1 of 130 papers40 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Fine-Tuning Language Models with Reward Learning on Policy
- Blog: Reward learning from human preferences and demonstrations in Atari
- Blog: Sequence Prediction with Unlabeled Data by Reward Function Learning
- Blog: Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning
- Blog: Reward Modeling from Natural Language Human Feedback
- Blog: Bridging Offline and Online Reinforcement Learning for LLMs
- Blog: Reward Fine-Tuning Two-Step Diffusion Models via Learning Differentiable Latent-Space Surrogate Reward
- Blog: Process Reinforcement through Implicit Rewards
- Blog: A Survey of Reinforcement Learning from Human Feedback
- Blog: Value Matching: Scalable and Gradient-Free Reward-Guided Flow Adaptation
- Blog: Fine-Tuning Hard-to-Simulate Objectives for Quadruped Locomotion: A Case Study on Total Power Saving
- Blog: Distributional Successor Features Enable Zero-Shot Policy Optimization
- Blog: Consequences of Misaligned AI
- Blog: Learning to Answer from Correct Demonstrations
- Blog: A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models
- Blog: From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
- Blog: PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards
- Blog: DiffusionReward: Enhancing Blind Face Restoration through Reward Feedback Learning
- Blog: Scaling Laws for Reward Model Overoptimization
- Blog: Deep Reinforcement Learning from Human Preferences
- Blog: RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
- Blog: Towards Efficient Exact Optimization of Language Model Alignment
- Blog: D2PO: Discriminator-Guided DPO with Response Evaluation Models
- Blog: Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression
- Blog: Real-Time Aligned Reward Model beyond Semantics
- Blog: Joint Reward and Policy Learning with Demonstrations and Human Feedback Improves Alignment
- Blog: FastGRPO: Accelerating Policy Optimization via Concurrency-aware Speculative Decoding and Online Draft Learning
- Blog: On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
- Blog: Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards
- Blog: DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Reward
History & citation
Current · Permanent link
- This direction split from Online Reward Modeling for Robust Alignment (77% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_online_reward_adaptation_a4ca9d20,
title = {online reward adaptation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/online-reward-adaptation/rdr_a4ca9d208b154dfa9e6692f25229bc43},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_online_reward_adaptation_a4ca9d20_v1,
title = {online reward adaptation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/online-reward-adaptation/rdr_a4ca9d208b154dfa9e6692f25229bc43/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}