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…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Constrained Reward Functions”
Self-distillation improves constrained language generation by aligning models with target distributions.
problem Sparse and uninformative reward signals in constrained generation settings.
method Iteratively refining the base model through self-distillation, incorporating learned twist functions and proposals.
result Substantial gains in generation quality through improved model alignment with target distributions.
Paper characterizes optimal language model alignment methods.
problem Aligning language models to maximize reward while keeping them close to the original model.
method KL-constrained reinforcement learning and best-of-N methods.
result Optimal KL-constrained RL solution has a large deviation principle rate function.
Proposes Constrained Q-learning for reinforcement learning with constraints.
problem Optimizing multiple objectives while adhering to constraints in reinforcement learning.
method Directly restricts the action space in Q-update to learn optimal Q-function for constrained MDP.
result Improves safety and optimality in high-level decision making for autonomous driving.
New algorithm reduces sample complexity for constrained MDPs.
problem Learning policies in constrained average-reward MDPs.
method Model-based algorithm for relaxed and strict feasibility settings.
result Achieves minimax-optimal bounds for constrained MDPs.
Novel evolutionary strategy solves stochastic constrained optimization problems.
problem Optimizing objective functions with stochastic constraints in reinforcement learning.
method Design of a novel optimization algorithm with a sufficient decrease mechanism for stochastic constrained problems.
result Demonstrated convergence of the algorithm on control tasks and constrained optimization problems.
Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While constraints may solve this issue, there is no closed form solution for general co…
Optimizing rewards under budget constraints with correlated costs and rewards.
problem Maximizing total expected reward under a budget constraint on total cost with correlated and potentially heavy-tailed cost-reward pairs.
method Proposes algorithms exploiting correlation between cost and reward via linear minimum mean-square error estimation to achieve tight regret bounds.
result Achieves regret for a budget under certain moment conditions.
New algorithm achieves optimal regret in average reward MDPs without prior bias information.
problem Achieving optimal regret in average reward MDPs with computational efficiency and without prior bias information.
method Projective Mitigated Extended Value Iteration (PMEVI) to compute bias-constrained optimal policies efficiently.
result First tractable algorithm with minimax optimal regret of .
Develops neural network framework for risk-reward optimization problems.
problem Multi-period risk-reward optimization with constrained policies.
method Neural network framework with two coupled feedforward networks, parametrizing two-step policies.
result Empirical optimum converges to true optimal value as network capacity and training size increase.
A significant challenge for the practical application of reinforcement learning in the real world is the need to specify an oracle reward function that correctly defines a task. Inverse reinforcement learning (IRL) seeks to avoid this challenge by instead inferring a reward function from expert behavior. While appealin…
FOCOPS optimizes agent's behavior while adhering to constraints.
problem Optimizing agent's behavior while respecting safety constraints.
method FOCOPS solves a constrained optimization problem in policy space, then projects the solution back into the parametric space.
result FOCOPS achieves better performance on constrained robotics tasks.
New algorithm learns safe policies in unknown environments.
problem Learning safe policies in unknown, potentially unsafe environments.
method C-UCRL: Upper Confidence Reinforcement Learning for constrained MDPs.
result Achieves sub-linear regret while satisfying constraints.
New method optimizes policies without assuming known link functions between preferences and rewards.
problem Policy alignment with unknown and unrestricted link functions.
method Formulates an -divergence-constrained reward maximization problem, learning policies directly.
result Induces a semiparametric single-index binary choice model for policy alignment.
A new algorithm uses concavity in Gaussian processes to optimize decisions in bandit problems.
problem Optimizing decisions in sequential problems with context-dependent rewards.
method Proposes a UCB algorithm using a shape-constrained reward function estimator based on a Gaussian Process model with concavity constraints.
result Derives regret bounds for the proposed UCB algorithm.
Study proposes adaptive RL for dynamic portfolio optimization.
problem Traditional portfolio optimization models fail to adapt to regime shifts.
method Regime-aware reinforcement learning framework with hybrid observations and constrained reward functions.
result Transformer PPO achieves highest risk-adjusted returns, while LSTM variants offer a good balance.
Eikonal-Constrained QRL improves goal-reaching in reinforcement learning.
problem Reward design and out-of-distribution generalization in reinforcement learning.
method Eikonal-Constrained Quasimetric Reinforcement Learning (Eik-QRL) using the Eikonal PDE.
result Eik-QRL achieves state-of-the-art performance in offline goal-conditioned navigation and manipulation tasks.
Unified framework for aligning and composing diffusion models to satisfy multiple constraints.
problem Improving quality and compliance of generated samples from diffusion models.
method Constrained optimization framework that unifies alignment and composition of diffusion models.
result Proposed framework effectively satisfies multiple constraints in image generation.
Reward suffices for convex MDPs, expanding RL to new problems.
problem Capturing goals as convex functions of stationary distribution.
method Reformulated as a min-max game using Fenchel duality.
result Convex MDPs require non-stationary reward functions.
A novel approach for safe offline RL using latent safety constraints.
problem Balancing safety constraints and reward maximization in offline RL.
method Conditional Variational Autoencoders for latent safety modeling, Constrained Reward-Return Maximization.
result Our approach maintains safety compliance while optimizing rewards, outperforming existing methods.
New algorithm for fair ranking in contextual bandits with concave rewards.
problem Fair ranking in recommendation systems.
method Geometric interpretation of CBCR as optimization, Frank-Wolfe analyses.
result First algorithm with provably vanishing regret for CBCR.
This paper shows how to solve complex reinforcement learning problems with zero duality gap.
problem Complex reinforcement learning problems with conflicting objectives.
method Formulate as a constrained RL problem and solve using Primal-Dual methods.
result The problem has zero duality gap, making it convex and solvable exactly in the dual domain.
PDCA algorithm learns policies for RL with constraints using a primal-dual approach.
problem Offline constrained reinforcement learning with general function approximation.
method Primal-Dual-Critic Algorithm (PDCA) using a primal-dual approach.
result PDCA finds a near saddle point of the Lagrangian, nearly optimal for constrained RL.
New algorithms boost SAT solver performance by optimizing restart strategies.
problem Optimizing decision-making under time constraints with restarts.
method Developed online learning algorithms for a bandit problem with controlled restarts.
result Achieved and regret bounds.
This study mainly investigates two common decoding problems in neural keyphrase generation: sequence length bias and beam diversity. To tackle the problems, we introduce a beam search decoding strategy based on word-level and ngram-level reward function to constrain and refine Seq2Seq inference at test time. Results sh…
New RL algorithm achieves sublinear regret and constraint violation without simulators.
problem Maximizing reward under utility constraints in large-scale systems.
method Model-free, simulator-free algorithm using LSVI-UCB with primal-dual optimization and soft-max policy.
result Achieves regret and constraint violation bounds.
A bandit algorithm reduces regret in noisy, communication-constrained feedback.
problem Distributed stochastic multi-armed bandit with noisy, communication-constrained feedback.
method Proposes a multi-phase bandit algorithm, UE-UCB++, that matches an information-theoretic lower bound.
result Matches an information-theoretic lower bound of Ω(√(KT/σ²)) on the minimax regret.
LinConTS improves regret and constraint violations in probabilistic linearly constrained bandits.
problem Maximizing cumulative reward under probabilistic linear constraints.
method LinConTS, a Thompson Sampling-based algorithm for bandits with linear constraints.
result LinConTS achieves O(log T) regret and constraint violations for suboptimal arms.
CoCoRL learns safe constraints from demonstrations with unknown rewards.
problem Learning safe constraints from demonstrations with different unknown rewards.
method Convex Constraint Learning for Reinforcement Learning (CoCoRL) constructs a convex safe set based on demonstrations.
result CoCoRL learns constraints that lead to safe driving behavior and can safely transfer to different tasks and environments.
We study contextual bandits with budget and time constraints, referred to as constrained contextual bandits.The time and budget constraints significantly complicate the exploration and exploitation tradeoff because they introduce complex coupling among contexts over time.Such coupling effects make it difficult to obtai…
Paper proposes a new risk measure (reward volatility) for optimizing financial decisions.
problem Managing uncertainty and volatility in financial decision-making.
method Defines reward volatility, derives policy gradient theorem, develops actor-only algorithm.
result Risk-averse optimization improves both reward volatility and return variance.
Policy gradient algorithms typically combine discounted future rewards with an estimated value function, to compute the direction and magnitude of parameter updates. However, for most Reinforcement Learning tasks, humans can provide additional insight to constrain the policy learning. We introduce a general method to i…
New algorithm for recommending best arms with aggregated feedback.
problem Finding the best arm under aggregated feedback when precise rewards are unavailable.
method Gaussian Process Optimistic Optimisation (GPOO) algorithm with adaptive tree construction.
result The proposed algorithm achieves new simple regret bounds with aggregated feedback.
Novel methods generate diverse policies in reinforcement learning.
problem Generating diverse policies in reinforcement learning.
method Constrained optimization perspective, introducing new metrics, and novel policy generation methods.
result Improved novelty and performance of generated policies.
Rectified Pessimistic-Optimistic Learning for Stochastic Continuum-armed Bandit with Constraintscs.LG
Paper tackles constrained bandit problems with a new learning framework.
problem Optimizing a black-box reward function subject to a black-box constraint function over a continuous space.
method Rectified Pessimistic-Optimistic Learning (RPOL) framework, incorporating optimistic and pessimistic GP bandit learning.
result RPOL achieves sublinear regret and minimal cumulative constraint violation.
Algorithm tackles constrained reinforcement learning with concave-convex and knapsack constraints.
problem Constrained episodic reinforcement learning with concave rewards and convex constraints.
method Modular analysis with strong theoretical guarantees for concave-convex and knapsack settings.
result Significantly outperforms existing approaches in constrained episodic environments.
Agents cooperate to make decisions in multi-armed bandits over a graph.
problem Optimizing decisions in multi-agent multi-armed bandits with shared information.
method Designs consensus-based distributed estimation and cooperative algorithms for group decision-making.
result Achieves group performance close to centralized fusion center.
New algorithm reduces regret and constraint violation in constrained bandit problems.
problem Optimizing under budget and stochastic constraints in resource-constrained settings.
method Lyapunov optimization methodology, algorithm.
result Achieves regret and zero constraint-violation for large .
Langevin Dynamics for Adaptive Inverse Reinforcement Learning of Stochastic Gradient Algorithmscs.LG
Paper proposes Langevin dynamics for adaptive IRL of stochastic gradient algorithms.
problem Estimating reward functions from noisy gradient estimates of stochastic gradient agents.
method Generalized Langevin dynamics algorithm for IRL.
result Proposed algorithms asymptotically generate samples proportional to exp(R(θ)).
We present a fully nonparametric method to estimate the value function, via simulation, in the context of expected infinite-horizon discounted rewards for Markov chains. Estimating such value functions plays an important role in approximate dynamic programming and applied probability in general. We incorporate "soft in…
Paper tackles best mixed arm identification with cost constraints in bandit models.
problem Finding the best mixed arm with cost constraints in a stochastic bandit model.
method Proposes SFSR algorithm combining successive reject and score-function-based rejection criteria.
result Upper and lower bounds on mis-identification probability show exponential decay with budget.
Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policycs.LG
This work tackles risk-sensitive deep RL by optimizing policies with variance constraints.
problem Risk and aleatoric uncertainty in deep reinforcement learning.
method Lagrangian and Fenchel dualities to transform the problem into an unconstrained saddle-point policy optimization problem, and an actor-critic algorithm to iteratively update policy, Lagrange multiplier, and Fenchel dual variable.
result The proposed actor-critic algorithm finds a globally optimal policy at a sublinear rate.
A new algorithm finds optimal solutions for constrained decision processes.
problem Optimizing state-value functions with constraints in CMDPs.
method Gradient-Aware Search (GAS) exploiting PWLC structure.
result GAS converges faster and more reliably than existing methods.
ACOL learns constraints from human preferences in driving simulations.
problem Learning constraints from human preferences in driving simulations.
method Adaptive Constraint Learning (ACOL) algorithm for constrained linear best-arm identification.
result ACOL's sample complexity matches worst-case lower bound and is significantly tighter in the average case.
DOPL learns from preference feedback to solve RMAB problems.
problem Learning optimal decisions in RMAB with limited reward information.
method Direct online preference learning (DOPL) for Pref-RMAB.
result DOPL achieves sublinear regret for RMAB with preference feedback.
Imitation Learning (IL) is an appealing approach to learn desirable autonomous behavior. However, directing IL to achieve arbitrary goals is difficult. In contrast, planning-based algorithms use dynamics models and reward functions to achieve goals. Yet, reward functions that evoke desirable behavior are often difficul…
New algorithms speed up inverse reinforcement learning by solving MDPs once.
problem Slow convergence in Maximum Entropy Inverse Reinforcement Learning.
method Deep Inverse Q-learning with constraints exploiting Q-learning.
result Up to several orders of magnitude speedup compared to existing methods.
New algorithm optimally identifies best arm in both stochastic and adversarial settings.
problem Best arm identification in stochastic and adversarial reward scenarios.
method Parameter-free algorithm designed to be robust to adversarial rewards and optimal in stochastic problems.
result Algorithm's error rate matches optimal bounds in stochastic problems and is robust to adversarial rewards.