Mitigates overoptimization in RLHF by reformulating SFT loss as a preference optimization loss.
problem Overoptimization in RLHF where reward model misguides generative model.
method Proposes a theoretical algorithm that minimizes maximum likelihood estimation and reward penalty, reformulates as simple objective combining preference optimization and supervised learning losses.
result Improved performance of RPO compared to DPO baselines in aligning LLMs.
Study scaling laws of reward model overoptimization in reinforcement learning.
problem Reward model overoptimization hinders true performance in reinforcement learning.
method Synthetic setup with fixed gold reward model; optimization using RL or best-of-n sampling; analysis of scaling laws. result Scaling laws of reward model overoptimization differ based on optimization method and scale smoothly with model parameters.
Improved DPO framework penalizes preference uncertainty to avoid overoptimization.
problem Aligning LLMs to human preferences is challenging due to varied, context-dependent, and ambiguous preferences.
method Developed a pessimistic framework for DPO by introducing preference uncertainty penalization schemes.
result Improved overall performance and better completions on high-uncertainty responses compared to vanilla DPO.
IDS improves RLHF by smoothing reward data, enhancing model performance.
problem Reward model performance degrades and overoptimization hinders true objective.
method Iterative Data Smoothing (IDS) updates model and data labels during each epoch.
result IDS outperforms traditional methods in RLHF.
Improved inference-time alignment using Best-of-N and smoothing.
problem Reward overoptimization in Best-of-N (BoN) due to poor proxy reward models.
method Introduced Soft Best-of-N (SBoN) and analyzed its performance through KL divergence and regret analysis.
result Smoothing helps SBoN mitigate reward overoptimization, especially when proxy reward quality is low.
Fine-tunes diffusion models to generate diverse samples with high genuine rewards.
problem Reward collapse in finetuning diffusion models.
method Entropy-regularized control against pretrained diffusion models.
result Efficient generation of diverse samples with high genuine rewards.
BRAID fine-tunes diffusion models to optimize reward models in offline scenarios.
problem Combining generative modeling and model-based optimization in offline scenarios.
method Conservative fine-tuning of diffusion models using RL to optimize reward models.
result BRAID outperforms existing methods in offline data, avoiding invalid designs.
Proposes a new RL method to fine-tune flow-based models with arbitrary rewards.
problem Challenges in fine-tuning continuous flow-based generative models with arbitrary reward functions.
method Online Reward-Weighted Conditional Flow Matching with Wasserstein-2 Regularization (ORW-CFM-W2)
result Achieves optimal policy convergence with controllable trade-offs between reward maximization and diversity preservation.
DRO-REBEL improves LLM alignment by robustly updating models online.
problem Overfitting and drifting of LLMs during RLHF.
method DRO-REBEL uses type-p Wasserstein, KL, and χ2 ambiguity sets for robust online updates. result DRO-REBEL achieves faster convergence and better performance than prior methods.
Dan Lovallo and Daniel Kahneman must be commended for their clear identification of causes and cures to the planning fallacy in "Delusions of Success: How Optimism Undermines Executives' Decisions" (HBR July 2003). Their look at overoptimism, anchoring, competitor neglect, and the outside view in forecasting is highly …
Monitoring the biomedical literature for cases of Adverse Drug Reactions (ADRs) is a critically important and time consuming task in pharmacovigilance. The development of computer assisted approaches to aid this process in different forms has been the subject of many recent works. One particular area that has shown pro…
There are several distinct failure modes for overoptimization of systems on the basis of metrics. This occurs when a metric which can be used to improve a system is used to an extent that further optimization is ineffective or harmful, and is sometimes termed Goodhart's Law. This class of failure is often poorly unders…
Paper proposes COM-QEL to avoid overoptimistic solutions in offline optimization.
problem Incorrect extrapolation of objective values in unexplored regions.
method Integrates quantum extremal learning with conservative objective models.
result COM-QEL finds higher true objective values compared to QEL.
EC method calibrates neural networks by matching average confidence to correct label proportion.
problem Overoptimism in neural network prediction confidence.
method Expectation consistency (EC) post-training rescaling of weights.
result EC achieves similar calibration performance to temperature scaling (TS) but is based on a principled Bayesian principle.
Reward hacking exploits misspecified rewards, affecting agent capabilities and true performance.
problem Reward hacking in RL models exploiting reward misspecifications.
method Constructed four RL environments with misspecified rewards; analyzed agent capabilities and behavior.
result More capable agents exploit reward misspecifications, achieving higher proxy reward but lower true reward.
Paper introduces PRMs to learn non-Markovian stochastic rewards for reinforcement learning.
problem Lack of structured representation for non-Markovian stochastic rewards in reinforcement learning.
method Introduces probabilistic reward machines (PRMs) and presents an algorithm to learn them from decision processes.
result Algorithm proves correct and convergent for learning PRMs from decision processes.
This work analyzes the value of future reward information in RL.
problem Analyzing the impact of knowing future rewards in reinforcement learning.
method Competitive analysis and worst-case reward distribution.
result Exact ratios between standard RL agents and those with future-reward lookahead.
Self-supervised reward prediction improves RL in sparse reward settings.
problem Data efficiency and sparse reward signals in reinforcement learning.
method Learning a state representation for reward prediction and using it to shape rewards.
result Self-supervised reward prediction enhances RL algorithms in single-goal environments.
The study categorizes reward errors in reinforcement learning, finding some can be beneficial.
problem Training language models with imperfect proxy rewards.
method Theoretical analysis of policy gradient optimization and categorization of reward errors.
result Reward errors can be benign or even beneficial, preventing policy from stalling.
Reward collapse occurs when ranking-based reward models yield uniform rewards for different prompts.
problem Reward collapse in aligning large language models with human preferences.
method Introduced a prompt-aware optimization scheme to derive closed-form expressions for reward distributions.
result Our prompt-aware utility functions significantly alleviate reward collapse during training.
Reward models need more than just accuracy for effective RLHF.
problem The effectiveness of reward models in RLHF is not fully understood.
method An optimization perspective to evaluate reward models.
result Reward models with low reward variance can lead to a flat optimization landscape, hindering performance.
Action guidance helps agents learn true objectives in games with sparse rewards.
problem Training agents in games with sparse rewards requires significant exploration.
method Action guidance, a novel technique that combines exploration with reward shaping.
result Action guidance enables agents to optimize true objectives efficiently.
Paper proposes RRD to learn proxy rewards for sparse delayed rewards in episodic reinforcement learning.
problem Learning from sparse and delayed rewards in reinforcement learning.
method Randomized Return Decomposition (RRD) algorithm to redistribute rewards.
result Substantial improvement over baseline algorithms in experiments.
Learning reward functions from data is a promising path towards achieving scalable Reinforcement Learning (RL) for robotics. However, a major challenge in training agents from learned reward models is that the agent can learn to exploit errors in the reward model to achieve high reward behaviors that do not correspond …
Enhances reward specification in RL with a novel language-based approach.
problem Reward specification in RL can lead to unintended, potentially harmful behaviours.
method Developed a novel class of language-based Reward Machines using RML's built-in memory.
result Can specify non-regular, non-Markovian reward functions for complex tasks.
We propose a generic, Bayesian, information geometric approach to the exploration--exploitation trade-off in multi-armed bandit problems. Our approach, BelMan, uniformly supports pure exploration, exploration--exploitation, and two-phase bandit problems. The knowledge on bandit arms and their reward distributions is su…
Many reinforcement-learning researchers treat the reward function as a part of the environment, meaning that the agent can only know the reward of a state if it encounters that state in a trial run. However, we argue that this is an unnecessary limitation and instead, the reward function should be provided to the learn…
Extends reinforcement learning alignment to scalar rewards, improving math reasoning.
problem Designing reinforcement learning algorithms for general LLM alignment.
method Introduces f-GRPO and f-HAL, estimating f-divergences between reward-aligned and unaligned distributions.
result Improves math reasoning RLVR tasks and mitigates reward hacking.
This work characterizes reward function partial identifiability and its impact on policy optimization.
problem Reward function partial identifiability in complex tasks.
method Formal characterisation of partial identifiability using various reward learning data sources.
result Unified framework for comparing data sources and downstream tasks by their invariances.
This paper introduces a new reward shaping method for average-reward reinforcement learning.
problem Speeding up convergence to an optimal policy in average-reward reinforcement learning tasks.
method Developed a temporal logic-based approach to automatically generate reward shaping functions.
result The optimal policy can be recovered using the proposed reward shaping framework.
While recent progress in deep reinforcement learning has enabled robots to learn complex behaviors, tasks with long horizons and sparse rewards remain an ongoing challenge. In this work, we propose an effective reward shaping method through predictive coding to tackle sparse reward problems. By learning predictive repr…
Paper generalizes reward distribution in multi-armed bandits with temporally-partitioned rewards.
problem Handling partial rewards distributed over multiple rounds in multi-armed bandits.
method Introduces Beta-spread property to generalize reward distribution, derives lower bound, and provides TP-UCB-FR-G algorithm.
result Improves regret upper bound for some scenarios using Beta-spread property.
We present a novel method for learning a set of disentangled reward functions that sum to the original environment reward and are constrained to be independently obtainable. We define independent obtainability in terms of value functions with respect to obtaining one learned reward while pursuing another learned reward…
New reward function improves GAIL performance in task-based environments.
problem Reward bias in adversarial imitation learning.
method Proposed a new reward function to overcome existing biases.
result New reward function outperforms existing methods in task-based environments.
A new method resolves non-identifiability in reward modeling using anchor labels.
problem Non-identifiability in reward modeling from pairwise preferences alone.
method Anchor-guided Variance-aware Reward Modeling (AVRM) framework.
result AVRM resolves non-identifiability and improves reward modeling performance.
Reinforcement learning usually uses the feedback rewards of environmental to train agents. But the rewards in the actual environment are sparse, and even some environments will not rewards. Most of the current methods are difficult to get good performance in sparse reward or non-reward environments. Although using shap…
New concept: reward hacking, where optimizing a flawed reward function can hurt performance.
problem Optimizing imperfect reward functions leads to poor performance.
method Formal definition and analysis of reward hacking, examining conditions for unhackability.
result Reward functions are usually hackable, making it hard to align AI with human values.
We propose RUDDER, a novel reinforcement learning approach for delayed rewards in finite Markov decision processes (MDPs). In MDPs the Q-values are equal to the expected immediate reward plus the expected future rewards. The latter are related to bias problems in temporal difference (TD) learning and to high variance p…
The paper tackles reinforcement learning with exogenous variables and rewards.
problem Exogenous state variables and rewards slow reinforcement learning by introducing uncontrolled variation.
method Formalizes exogenous state variables and rewards, decomposes MDP into exogenous and endogenous components, and introduces algorithms to discover these components.
result Optimal policies for the endogenous MDP are also optimal for the original MDP, but the endogenous MDP is easier to solve due to reduced variance.
Study optimal reward schemes for inducing desired player performance in risky contests.
problem Designing optimal rewards to encourage desired performance levels in risky contests.
method Analyzed the optimal reward schemes for inducing average and specific rank performance.
result Optimal reward schemes can have surprising shapes, not just related to inequality.
Reinforcement Learning (RL) agents require the specification of a reward signal for learning behaviours. However, introduction of corrupt or stochastic rewards can yield high variance in learning. Such corruption may be a direct result of goal misspecification, randomness in the reward signal, or correlation of the rew…
Develops HMRL for sparse reward RL problems, improving meta policy efficiency and transferability.
problem Difficulty in learning meta policies for sparse reward RL problems.
method Hyper-Meta RL framework with cross-environment meta state embedding and shaped meta reward.
result Improves meta policy generalization and efficiency for sparse reward RL problems.
New RL algorithms improve average-reward performance.
problem Improving RL algorithms for average-reward criteria.
method Developed novel algorithms addressing average-reward criterion directly.
result ATRPO significantly outperforms TRPO in challenging MuJuCo environments.
Method predicts future rewards from past actions in a linear Gaussian system.
problem Maximizing cumulative reward in a stochastic multi-armed bandit with linear Gaussian dynamics.
method Proposes a method using a modified Kalman filter to predict future rewards based on past rewards.
result Reward from any action can be used to predict another action's future reward.
Paper addresses reward hacking in preference optimization, proposing POWER-DL to improve AI alignment.
problem Reward hacking problem in preference optimization, leading to undesired behaviors.
method POWER-DL combines robust reward maximization and dynamic label updates to mitigate reward hacking.
result POWER-DL consistently outperforms state-of-the-art methods on alignment benchmarks.
DDO-RM improves reward-based policies by converting reward scores into a target distribution.
problem Improving reward-based policies when the reward function is simpler than the policy.
method Converts reward scores into a target distribution and uses KL-regularized mirror-descent updates.
result DDO-RM outperforms DPO in pair accuracy and mean margin.
No real-world reward function is perfect. Sensory errors and software bugs may result in RL agents observing higher (or lower) rewards than they should. For example, a reinforcement learning agent may prefer states where a sensory error gives it the maximum reward, but where the true reward is actually small. We formal…
Trade-R1 bridges verifiable rewards to stochastic financial markets via process-level reasoning verification.
problem Extending RL to financial markets where rewards are verifiable but noisy.
method A verification method that transforms reasoning over financial documents into a structured RAG task, using a triangular consistency metric.
result DSR achieves superior cross-market generalization while maintaining reasoning consistency.