Reward tweaking optimizes behavior for long-term goals by adjusting the reward function.
problem Optimizing behavior for long-term goals in reinforcement learning with unstable long planning horizons.
method Reward tweaking learns a surrogate reward function that induces optimal behavior for the original task.
result Reward tweaking guides agents towards better long-term returns while planning for short horizons.
New conditions show proxy data can improve policy learning in sparse expert data contexts.
problem Improving sample complexity of policy learning with sparse expert data.
method Sufficient conditions for proxy data to improve sample complexity, adaptable to LLMs.
result Provable improvement in sample complexity for policy learning with proxy data.
Time series classification has received great attention over the past decade with a wide range of methods focusing on predictive performance by exploiting various types of temporal features. Nonetheless, little emphasis has been placed on interpretability and explainability. In this paper, we formulate the novel proble…
A contextual bandit method evaluates and improves inventory control policies.
problem Evaluating and improving periodic review inventory control policies with nonstationary demand.
method Contextual bandit-based algorithm to evaluate and tweak policies.
result The method achieves favorable guarantees in both theory and practice.
A new method generates meta-tasks using generative models for unsupervised learning.
problem Creating synthetic meta-tasks for unsupervised learning.
method Generative models with latent space interpolation for sampling.
result The method outperforms or is competitive with baselines on few-shot classification tasks.
Eigenvalues of Steklov eigenproblems change predictably with boundary tweaks.
problem Understanding how Steklov eigenvalues respond to boundary changes.
method Analyzing smooth boundary perturbations of Steklov eigenvalues.
result Steklov eigenvalues are generically simple under such perturbations.
The classical trefoil is famous for having a three-colouring which distinguishes it from the unknot. The three-colouring is also notorious for not distinguishing the right handed from the left handed trefoil. However with a bit of tweaking the three colours can also be used for this task. What lies behind the method is…
This paper studies the performance of a recently proposed preconditioned stochastic gradient descent (PSGD) algorithm on recurrent neural network (RNN) training. PSGD adaptively estimates a preconditioner to accelerate gradient descent, and is designed to be simple, general and easy to use, as stochastic gradient desce…
In considering the mathematical problem of describing the geodesics on a torus or any other surface of revolution, there is a tremendous advantage in conceptual understanding that derives from taking the point of view of a physicist by interpreting parametrized geodesics as the paths traced out in time by the motion of…
Adversarial examples are maliciously tweaked images that can easily fool machine learning techniques, such as neural networks, but they are normally not visually distinguishable for human beings. One of the main approaches to solve this problem is to retrain the networks using those adversarial examples, namely adversa…
Efficient deep learning computing requires algorithm and hardware co-design to enable specialization: we usually need to change the algorithm to reduce memory footprint and improve energy efficiency. However, the extra degree of freedom from the algorithm makes the design space much larger: it's not only about designin…
We present SEBOOST, a technique for boosting the performance of existing stochastic optimization methods. SEBOOST applies a secondary optimization process in the subspace spanned by the last steps and descent directions. The method was inspired by the SESOP optimization method for large-scale problems, and has been ada…
Paper forecasts tax revenues in Bulgaria during pandemic.
problem Forecasting tax revenues during pandemic.
method Model based on IMF recommendations, using 1995-2019 data.
result Pandemic negatively impacts tax revenues, but econometrics can still produce forecasts.
LLMs produce volatile sentence-level sentiment classifications that affect financial decision-making.
problem Volatile outputs from LLMs impact financial text understanding tasks.
method Case study on US equity market investing via news sentiment analysis.
result Volatile LLM outputs lead to significant variations in portfolio construction and returns.
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.
Improved analysis shows momentum in SGD reduces batch size needs for non-convex objectives.
problem Reducing batch size requirements for SGD in non-convex optimization.
method Normalized SGD with momentum, adaptive method for small gradient variance.
result Normalized SGD with momentum achieves ε-critical points in O(1/ε3.5) iterations. 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.
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.
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.
Proposes a method to boost deep reinforcement learning with sparse rewards.
problem Challenges in learning complex behaviors with long horizons and sparse rewards.
method Predictive coding for reward shaping.
result Achieves better learning by providing reward signals that understand environment dynamics and emphasize useful features.
The performance of Feedforward neural network (FNN) fully de-pends upon the selection of architecture and training algorithm. FNN architecture can be tweaked using several parameters, such as the number of hidden layers, number of hidden neurons at each hidden layer and number of connections between layers. There may b…
Quantum-enhanced metrology aims to estimate an unknown parameter such that the precision scales better than the shot-noise bound. Single-shot adaptive quantum-enhanced metrology (AQEM) is a promising approach that uses feedback to tweak the quantum process according to previous measurement outcomes. Techniques and form…
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.
New RL method uses distance between states instead of rewards for sparse reward environments.
problem Sparse rewards or non-reward environments in reinforcement learning.
method Uses goal-distance gradient and bridge point planning for policy improvement.
result Significantly better performance on sparse reward and local optimal problems in complex environments.
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.
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.
We introduce an algorithm for the pricing of finite expiry American options driven by Lévy processes. The idea is to tweak Carr's `Canadisation' method, cf. Carr [9] (see also Bouchard et al [5]), in such a way that the adjusted algorithm is viable for any Lévy process whose law at an independent, exponentially distrib…
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.
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.
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…
Method distills reward and strategies from diverse demonstrators.
problem Reward ambiguity and heterogeneity in human demonstrations.
method Reward network distillation to infer task goal and strategies.
result Better recovery of task and strategy rewards.
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.
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.