This study examines how reward scaling impacts non-saturating ReLU networks in reinforcement learning.
problem The impact of reward scaling on non-saturating ReLU networks in reinforcement learning.
method Proposes an Adaptive Network Scaling framework to find a suitable reward scale during learning.
result Empirical studies justify the effectiveness of the Adaptive Network Scaling framework.
This work shows how approximate reward models can significantly improve inference-time scaling.
problem Improving the efficiency of inference for large language models.
method Identifying the Bellman error of approximate reward models and using Sequential Monte Carlo (SMC) for inference.
result Approximate reward models can reduce computational complexity from exponential to polynomial in T T T . 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 n n sampling; analysis of scaling laws. result Scaling laws of reward model overoptimization differ based on optimization method and scale smoothly with model parameters.
Study shows curiosity-driven learning can perform well without extrinsic rewards.
problem Lack of scalable methods for intrinsic reward design in reinforcement learning.
method Performed a large-scale study of curiosity-driven learning across 54 environments, using prediction error as reward.
result Curiosity-driven learning can achieve good performance without extrinsic rewards, aligning with hand-designed rewards in many cases.
New method predicts and optimizes test-time scaling for LLMs.
problem Lack of principled guidance on scaling LLMs efficiently.
method Tail-guided search to predict and allocate compute.
result SLG Search achieves higher rewards with less compute.
New algorithm handles MDPs with unknown, changing rewards efficiently.
problem Handling MDPs with unknown, changing rewards in large state spaces.
method Developed an algorithm with O ( τ ( ln ∣ S ∣ + ln ∣ A ∣ ) T ln ( T ) ) O(\sqrt{τ(\ln|S|+\ln|A|)T}\ln(T)) O ( τ ( ln ∣ S ∣ + ln ∣ A ∣ ) T ln ( T )) regret bound and a modified algorithm with polynomial complexity. result Achieved state-of-the-art regret bounds for large scale MDPs with changing rewards.
SA-GFN corrects biases in GFlowNets due to graph symmetries.
problem Systematic biases in state transition probability computations.
method Incorporates symmetry corrections into the learning process through reward scaling.
result Eliminates need for explicit state transition computations.
The paper enhances preference learning by incorporating response time data.
problem Lack of temporal information in user decision-making for reward model learning.
method Integrates response time alongside binary choice data using the EZ model and Neyman-orthogonal loss functions.
result Response time-augmented approach reduces error rates from exponential to polynomial scaling, improving sample efficiency.
The abstract explores connections between reinforcement learning, scaling, and diffusion.
problem Aligning reinforcement learning with human feedback and scaling techniques.
method Clarifying connections between reinforcement learning, scaling, and diffusion.
result Introducing a resampling approach for alignment and reward-directed diffusion models.
New algorithm improves inference-time alignment without reward hacking.
problem Improving quality of responses from language models with limited compute.
method Inference-time alignment, focusing on e x t t t I n f e r e n c e T i m e P e s s i m i s m exttt{InferenceTimePessimism} e x ttt I n f er e n ce T im e P ess imi s m algorithm. result Optimal performance and scaling-monotonicity of e x t t t I n f e r e n c e T i m e P e s s i m i s m exttt{InferenceTimePessimism} e x ttt I n f er e n ce T im e P ess imi s m . Improves generative models by optimizing rewards and sample editing.
problem Efficiently generating high-reward samples with structural constraints.
method Introduces MDM-VGB, a discrete diffusion sampler that augments unmasking generation with reward-guided remasking.
result MDM-VGB achieves quadratic complexity and robustness to noise, outperforming heuristics like best-of- N N N . Reward-free RL in linear MDPs is as hard as reward-aware RL.
problem Reward-free RL in linear MDPs without access to the reward function during exploration.
method Developed a computationally efficient algorithm with sample complexity O ~ ( d 2 H 5 / ε 2 ) \widetilde{\mathcal{O}}(d^2 H^5/ε^2) O ( d 2 H 5 / ε 2 ) . result Achieved optimal d d d dependence in linear MDPs for reward-free RL, matching the reward-aware RL setting. Paper addresses reward learning issues in RL, improving both under- and over-estimation.
problem Reward learning from data can lead to reward delusions or underestimation, causing unintended behaviors.
method Connects reward learning to positive-unlabeled (PU) learning and applies a large-scale PU learning algorithm.
result Improves both GAIL and supervised reward learning without additional assumptions.
Unified algorithm for optimizing rewards in stochastic path problems.
problem Optimizing rewards in stochastic path problems with unknown reward scales.
method A simple optimistic algorithm with regret guarantees.
result Regret bound matches best known results for SSP with all non-positive rewards.
Solves reinforcement learning reward design for user-aligned agents.
problem Designing effective reward functions for reinforcement learning.
method Reward modeling: learn from user interaction and optimize.
result Agents can be aligned with user intentions through learned reward functions.
Improves RLHF sample efficiency by scaling reward complexity polynomially.
problem Exponential sample complexity in RLHF algorithms for skewed preferences.
method SE-POPO, an online RLHF algorithm that achieves polynomial sample complexity.
result SE-POPO outperforms existing algorithms in sample efficiency.
Adapts deep reinforcement learning to ordinal rewards.
problem Using numerical rewards in reinforcement learning has drawbacks; ordinal rewards offer an alternative.
method Develops a general approach to converting reinforcement learning algorithms to ordinal reward systems, including Ordinal Deep Q-Networks.
result Ordinal Deep Q-Networks perform comparably to numerical variants on engineered problems and better on simpler reward signals.
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.
Thompson Sampling shows polynomial regret for combinatorial semi-bandits with subgaussian rewards.
problem Finding optimal solutions in combinatorial semi-bandits with suboptimal sampling.
method Proposes Thompson Sampling with polynomial regret for linear combinatorial semi-bandits.
result Demonstrates 'mismatched sampling paradox' where knowing distributions can lead to worse performance.
New model for display advertising with stochastic and adversarial components.
problem Display advertising with stochastic and adversarial click-through-rates.
method Adversarial scaling model; two algorithms tested: action elimination and mirror descent.
result Two algorithms are robust to adversarial scaling.
Adaptive exploration scheme for evaluating multiple policies with different rewards.
problem Online multi-reward multi-policy evaluation.
method Adapted ( ε , δ ) (ε,δ) ( ε , δ ) -PAC perspective and MR-NaS exploration scheme to minimize sample complexity. result Demonstrated effectiveness of adaptive exploration in tabular domains.
New algorithm uses GNNs to optimize rewards in graph-structured data.
problem Optimizing rewards in molecule design with graph-structured data.
method Embedding permutation invariance into GNNs and using GNTK for regret bounds.
result First GNN confidence bound and phased-elimination algorithm with sublinear regret.
Bayesian REX learns Atari games from demonstrations efficiently.
problem Bayesian reward learning for complex control problems is computationally intractable.
method Bayesian Reward Extrapolation (Bayesian REX) pre-trains a low-dimensional feature encoding and uses preferences to perform fast Bayesian inference.
result Bayesian REX learns Atari games from demonstrations in 5 minutes, competitive with state-of-the-art methods.
The paper develops a robust algorithm for contextual bandits with heavy-tailed rewards.
problem Contextual bandits with heavy-tailed rewards.
method Develops an algorithm based on Catoni's estimator for robust statistics, applying it to contextual bandits with general function approximation.
result Establishes regret bounds that depend on cumulative reward variance and logarithmically on the reward range and number of rounds.
We introduce a framework to study the effective objectives at different time scales of financial market microstructure. The financial market can be regarded as a complex adaptive system, where purposeful agents collectively and simultaneously create and perceive their environment as they interact with it. It has been s…
Best-of-Majority improves inference performance in Pass@ k k k settings.
problem Inference in difficult tasks often underperforms with single-shot selection methods.
method Combining majority voting and Best-of-N, Best-of-Majority restricts candidates to high-frequency responses.
result Best-of-Majority achieves minimax optimal regret and outperforms other methods.
Study quantile reward identification with 1-bit feedback constraints.
problem Best arm identification with quantile reward and 1-bit communication.
method Proposes an algorithm using noisy binary search for quantile reward estimation.
result Derives upper and lower bounds on sample complexity for 1-bit feedback.
New method learns Atari game Montezuma's Revenge from a single demonstration.
problem Learning from sparse rewards in complex exploration tasks.
method Maximizing rewards directly from a single demonstration state, combined with off-the-shelf reinforcement learning.
result Trained agent achieves high-score of 74,500 in Montezuma's Revenge.
A new UCB policy improves reward-cost ratio estimation in budgeted MAB.
problem Maximizing reward-cost ratio under budget constraints.
method ω-UCB policy with asymmetric confidence intervals.
result Logarithmic regret and superior performance in various settings.
Two novel methods identify influential features in CMABs for better reward distribution.
problem Suboptimal features degrade rewards, interpretability, and efficiency in CMABs.
method Heterogeneous Incremental Effect (HIE) and Heterogeneous Distribution Divergence (HDD) methods.
result Consistent ability to identify influential HTE features, enhancing CMAB performance.
PRISM integrates diverse rewards in MORL, improving sample efficiency and Pareto coverage.
problem Heterogeneous MORL where dense objectives dominate, leading to poor sample efficiency.
method PRISM uses reflectional symmetry and ReSymNet to reconcile temporal-frequency mismatches and accelerate exploration.
result PRISM consistently outperforms sparse-reward baselines and oracles, achieving significant Pareto gains.
A new approach for deep exploration in sparse reward reinforcement learning.
problem Slow or no learning in reinforcement learning with rare rewards.
method Long-term visitation count planning and decoupling exploration and exploitation.
result Significantly outperforms existing methods in sparse reward environments.
We optimize saddle-point problems for large-scale Markov decision processes.
problem Optimizing policies in large-scale Markov decision processes.
method Characterized conditions for convergence and designed an optimization algorithm.
result Our algorithm converges faster and is state-space independent.
New algorithm for multi-player bandits without needing lower bounds or scaling inversely.
problem Multi-player bandits without collision sensing information.
method Proposes a novel algorithm that circumvents two problems of existing algorithms.
result Proves a theoretical regret upper bound and shows superior performance in practice.
Optimizes reward learning design for complex tasks using nonparametric methods.
problem Challenges in specifying reward functions for complex tasks.
method Models rewards and policies as nonparametric functions in RKHSs, derives risk bounds, and optimizes query design.
result Derives non-asymptotic excess risk bounds and finite sample statistical rates for reward learning.
A new method uses optimal transport for imitation learning, improving efficiency and performance.
problem Recovering expert policies from demonstrations with efficient and general reward functions.
method Proposes Wasserstein Adversarial Imitation Learning, using Kantorovich potentials as reward functions and regularized optimal transport.
result Significantly improves sample-efficiency and average cumulative rewards in robotic experiments.
Calibrated PRMs improve inference efficiency for LLMs by dynamically adjusting compute budgets.
problem Poor calibration of PRMs leads to overestimation of success probabilities in partial reasoning steps.
method Quantile regression for calibration, instance-adaptive scaling (IAS) framework.
result Calibrated PRMs reduce inference costs while maintaining accuracy, especially on confident problems.
BERT embeddings improve sequence quality metrics.
problem Measuring the quality of generated sequences against references.
method Employ contextual BERT embeddings for sequence-level reward.
result Contextual embeddings provide a more effective learning signal.
Robust Q-learning algorithm resists corrupted rewards.
problem Non-ideal environments with corrupted rewards.
method Developed a novel robust Q-learning algorithm using historical data.
result Finite-time convergence rate matches state-of-the-art bounds.
Method uses ANN to estimate incentive salience from large behavioral data.
problem Estimating incentive salience in naturalistic settings.
method Artificial Neural Networks (ANNs) for latent state approximation.
result ANNs produce better representations for predicting future behaviour.
A new policy for contextual bandits adapts to reward vector shifts.
problem Learning under reward vector shifts with ordered rewards.
method Adaptive-discretization and optimistic elimination policy.
result Established upper bounds on preference-based regret.
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.
This work compares human feedback methods for reward learning in bandits.
problem Understanding how human feedback affects the performance of reward learning methods.
method Theoretical comparison of human feedback approaches in offline contextual bandits.
result Human bias and uncertainty in feedback modeling impact the theoretical guarantees of reward learning methods.
New algorithms reduce contextual bandits' regret without knowing reward noise variances.
problem Reducing regret in contextual bandits with unknown reward noise variances.
method Developed new algorithms based on the optimism principle.
result Regret scales as the square root of the sum of measurement variances, not the time horizon.
Optimal strategy proposed for maximizing cumulative reward in continuum-armed bandits.
problem Maximizing cumulative reward in a scenario with limited resources and unknown stochastic rewards.
method Proposed an optimal strategy for a nonparametric setting with side information on actions.
result Optimal regret scales as \(O(T^{1/3})\) up to poly-logarithmic factors when \(T\) is proportional to \(N\).
We consider stochastic multi-armed bandit problems with complex actions over a set of basic arms, where the decision maker plays a complex action rather than a basic arm in each round. The reward of the complex action is some function of the basic arms' rewards, and the feedback observed may not necessarily be the rewa…
Improves text-to-image diffusion models using GFlowNets.
problem Aligning diffusion models with text descriptions.
method Post-training diffusion models with GFlowNets to generate high-reward images.
result Effective alignment of large-scale text-to-image diffusion models with reward information.
Thompson Sampling fails to perform well in high dimensions.
problem Thompson Sampling's suboptimality in high-dimensional combinatorial semi-bandits.
method Analysis of TS for combinatorial semi-bandits, including non-linear and linear reward functions, with Bernoulli rewards and uniform priors.
result TS's regret scales exponentially in the ambient dimension and minimax regret scales almost linearly in high dimensions.