No article text was recorded for this version.
reward function ambiguity
Version 2 of 2308 papers439 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Invariance in Policy Optimisation and Partial Identifiability in Reward Learning
- Blog: Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse Reinforcement Learning
- Blog: RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs
- Blog: Identifiability in inverse reinforcement learning
- Blog: Impossibility of deducing preferences and rationality from human policy
- Blog: Inverse Reinforcement Learning with Multiple Planning Horizons
- Blog: Failure Modes of Learning Reward Models for LLMs and other Sequence Models
- Blog: When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
- Blog: Reward Identification in Inverse Reinforcement Learning
- Blog: Theory of Mind and Preference Learning at the Interface of Cognitive Science, Neuroscience, and AI: A Review
- Blog: Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning
- Blog: Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning
- Blog: Identifying Reward Functions using Anchor Actions
- Blog: Towards Theoretical Understanding of Inverse Reinforcement Learning
- Blog: A Bayesian Approach to Robust Inverse Reinforcement Learning
- Blog: Towards Theoretical Understanding of Inverse Reinforcement Learning
- Blog: Global Bandits with Holder Continuity
- Blog: Invariance in Policy Optimisation and Partial Identifiability in Reward Learning
- Blog: Occam's razor is insufficient to infer the preferences of irrational agents
- Blog: Stochastic Inverse Reinforcement Learning
- Blog: Towards Generalized Inverse Reinforcement Learning
- Blog: Occam's razor is insufficient to infer the preferences of irrational agents
- Blog: Towards Theoretical Understanding of Inverse Reinforcement Learning
- Blog: Inverse Reinforcement Learning From Like-Minded Teachers
- Blog: Partial Identifiability in Inverse Reinforcement Learning For Agents With Non-Exponential Discounting
- Blog: Models of human preference for learning reward functions
- Blog: Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization
- Blog: A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challenges
- Blog: Classification structurée pour l'apprentissage par renforcement inverse
- Blog: Reinforcement Learning with a Corrupted Reward Channel
- Blog: Efficient Inverse Multiagent Learning
- Blog: When Your AIs Deceive You: Challenges with Partial Observability of Human Evaluators in Reward Learning
- Blog: Inverse Optimal Control with Linearly-Solvable MDPs
- Blog: Contextual Policies Enable Efficient and Interpretable Inverse Reinforcement Learning for Populations
- Blog: Models of human preference for learning reward functions
- Blog: Evaluating Strategic Structures in Multi-Agent Inverse Reinforcement Learning
- Blog: In-Trajectory Inverse Reinforcement Learning: Learn Incrementally From An Ongoing Trajectory
- Blog: Invariance in Policy Optimisation and Partial Identifiability in Reward Learning
- Blog: Provably Efficient Learning of Transferable Rewards
- Blog: A Survey of Reinforcement Learning from Human Feedback
- Blog: Inverse Reinforcement Learning with Sub-optimal Experts
- Blog: Identifiability and Generalizability in Constrained Inverse Reinforcement Learning
- Blog: Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees
- Blog: Invariance in Policy Optimisation and Partial Identifiability in Reward Learning
- Blog: On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference
- Blog: Reward Identification in Inverse Reinforcement Learning
- Blog: Partial Identifiability in Inverse Reinforcement Learning for Agents with Non-Exponential Discounting
- Blog: On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning
- Blog: Regularized Inverse Reinforcement Learning
- Blog: Robustness in the Face of Partial Identifiability in Reward Learning
- Blog: PAGAR: Imitation Learning with Protagonist Antagonist Guided Adversarial Reward
- Blog: On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization
- Blog: Imitating careful experts to avoid catastrophic events
- Blog: Statistical analysis of Inverse Entropy-regularized Reinforcement Learning
- Blog: AMBER: An Entropy Maximizing Environment Design Algorithm for Inverse Reinforcement Learning
- Blog: Learning from Failures: Understanding LLM Alignment through Failure-Aware Inverse RL
- Blog: Recovering Hidden Reward in Diffusion-Based Policies
- Blog: Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization
- Blog: What Is It You Really Want of Me? Generalized Reward Learning with Biased Beliefs about Domain Dynamics
- Blog: Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment
Showing 60 of 308 papers.
History & citation
Current · Permanent link
- Inverse Constrained Reinforcement Learning for Safe Imitation merged into this direction (61% overlap)
- behavioral model misspecification split from this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_reward_function_ambiguity_35529a5f,
title = {reward function ambiguity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/reward-function-ambiguity/rdr_35529a5f5db34cad92d4baa7e324c7b1},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_reward_function_ambiguity_35529a5f_v2,
title = {reward function ambiguity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/reward-function-ambiguity/rdr_35529a5f5db34cad92d4baa7e324c7b1/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}