Off-policy stochastic actor-critic methods rely on approximating the stochastic policy gradient in order to derive an optimal policy. One may also derive the optimal policy by approximating the action-value gradient. The use of action-value gradients is desirable as policy improvement occurs along the direction of stee…
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “natural policy gradient”
Rank-1 Approximation of Inverse Fisher for Natural Policy Gradients in Deep Reinforcement Learningcs.LG
Paper presents a rank-1 approximation method for natural policy gradients in deep RL.
problem Computing natural gradients requires inverting the Fisher Information Matrix, which is computationally expensive.
method Develops a rank-1 approximation to the inverse Fisher Information Matrix for efficient natural policy optimization.
result The rank-1 approximation converges faster and has similar sample complexity to stochastic policy gradient methods.
DSPI connects natural policy gradient to policy iteration, proving global convergence.
problem Optimizing policies in reinforcement learning.
method DSPI framework, combining smoothed policy iteration and natural policy gradient.
result DSPI achieves geometric convergence and optimal complexity for policy optimization.
New method for natural policy gradients converges linearly.
problem Improving natural policy gradient methods for better convergence.
method Fisher-Rao gradient flow applied to state-action distributions.
result Linear convergence rate with geometry-dependent factor.
Trust-region methods have yielded state-of-the-art results in policy search. A common approach is to use KL-divergence to bound the region of trust resulting in a natural gradient policy update. We show that the natural gradient and trust region optimization are equivalent if we use the natural parameterization of a st…
Solves POMDPs with recurrent neural networks and natural policy gradient.
problem Non-stationarity in optimal policies of POMDPs.
method Integrates recurrent neural networks into natural policy gradient and temporal difference learning.
result Non-asymptotic theoretical guarantees for global optimality up to function approximation.
Accelerating Quantum Reinforcement Learning with a Quantum Natural Policy Gradient Based Approachquant-ph
A quantum reinforcement learning algorithm reduces sample complexity.
problem Quantum reinforcement learning under model-free settings with quantum oracle access.
method Quantum Natural Policy Gradient (QNPG) algorithm replacing random sampling with deterministic gradient estimation.
result QNPG achieves a sample complexity of for queries to the quantum oracle, significantly improving classical lower bound.
Large deviations theory applied to policy gradient methods.
problem Understanding convergence of policy gradient methods in reinforcement learning.
method Large deviation rate function and contraction principle from large deviations theory.
result Convergence properties of policy gradient methods can be extended to various policy parametrizations.
New algorithm for risk-sensitive reinforcement learning with natural policy gradients.
problem Risk-sensitive reinforcement learning with downside risk constraints.
method Introduce a new Bellman equation to estimate the lower partial moment of returns, use natural policy gradients, and extend Reward Constrained Policy Optimization.
result Sample-efficient estimation of partial moments and effective risk-sensitive control.
Paper develops NPG for risk-averse RL with ECRMs, proving global convergence.
problem Ensuring reliable performance in stochastic RL problems with risk-averse policies.
method Developed natural policy gradient updates for ECRMs-based RL problems, proving global optimality and iteration complexity.
result Global convergence of risk-averse NPG algorithm with ECRMs.
Entropy-regularized NPG methods converge linearly in discounted MDPs.
problem Theoretical limitations of NPG methods in reinforcement learning.
method Entropy regularization in conjunction with NPG methods for discounted MDPs.
result Entropy-regularized NPG methods converge linearly in discounted MDPs.
Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RLcs.LG
Optimistic NPG improves policy optimization in online RL with efficient sample complexity.
problem Limited theoretical understanding of policy optimization, especially in online RL.
method Combines natural policy gradient with optimistic policy evaluation.
result Achieves optimal dimension dependence sample complexity for learning near-optimal policies.
Proposes CoPO, a new policy optimization method for competitive games.
problem Designing efficient optimization methods for competitive Markov decision processes.
method Competitive policy optimization (CoPO) approach that exploits game-theoretic nature of competitive games.
result Stable optimization, convergence to sophisticated strategies, and higher scores compared to baseline methods.
The recently proposed option-critic architecture Bacon et al. provide a stochastic policy gradient approach to hierarchical reinforcement learning. Specifically, they provide a way to estimate the gradient of the expected discounted return with respect to parameters that define a finite number of temporally extended ac…
PPO's gradients are heavy-tailed, affecting learning; a robust estimator improves performance.
problem Heavy-tailedness of PPO gradients causing learning issues.
method Characterized heavy-tailed gradients, identified likelihood ratios and advantages as sources, proposed GMOM as a robust estimator.
result GMOM improves PPO performance without clipping tricks.
We develop a normative framework for hierarchical model-based policy optimization based on applying second-order methods in the space of all possible state-action paths. The resulting natural path gradient performs policy updates in a manner which is sensitive to the long-range correlational structure of the induced st…
Symmetric (Optimistic) Natural Policy Gradient for Multi-agent Learning with Parameter Convergencemath.OC
New NPG variants ensure parameter convergence in multi-agent learning.
problem Non-convergence of parameters in NPG for multi-agent learning.
method Proposed variants of NPG for multi-agent learning scenarios.
result Global last-iterate parameter convergence guarantees in various multi-agent learning settings.
New algorithm reduces complexity in multi-agent reinforcement learning.
problem High computational complexity in exact computations for multi-agent reinforcement learning.
method Design of a scalable algorithm based on Natural Policy Gradient, using local information and limited communication.
result Converges to globally optimal policy with dimension-free complexity and localization error.
Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximationcs.LG
Entropy-regularized NPG converges linearly with linear function approximation.
problem Analyzing convergence of entropy-regularized NPG with function approximation.
method Established finite-time convergence analyses with entropy regularization and linear function approximation.
result Entropy-regularized NPG achieves linear convergence up to a function approximation error.
Policy gradient methods with actor-critic schemes demonstrate tremendous empirical successes, especially when the actors and critics are parameterized by neural networks. However, it remains less clear whether such "neural" policy gradient methods converge to globally optimal policies and whether they even converge at …
Policy Gradient Methods Find the Nash Equilibrium in N-player General-sum Linear-quadratic Gamesmath.OC
Policy gradient methods find Nash equilibrium in noisy games.
problem Finding Nash equilibrium in noisy games.
method Policy gradient methods with noise added.
result Policy gradient methods converge to Nash equilibrium in noisy games.
This work learns exploration policies for unknown distributions using samples and policy gradients.
problem Learning exploration policies for unknown distributions in Bayesian bandits.
method Meta-learning approach parameterizing policies in a differentiable way and optimizing them with policy gradients.
result Effective gradient estimators and variance reduction techniques are derived.
This paper studies GAIL's global convergence for general MDP and nonlinear rewards.
problem Understanding when GAIL algorithms achieve global convergence for general MDP and nonlinear rewards.
method Characterization of global convergence for various policy gradient algorithms applied to GAIL.
result First systematic theoretical study of GAIL for global convergence.
Policy Gradient (PG) algorithms are among the best candidates for the much-anticipated applications of reinforcement learning to real-world control tasks, such as robotics. However, the trial-and-error nature of these methods poses safety issues whenever the learning process itself must be performed on a physical syste…
Many currently deployed Reinforcement Learning agents work in an environment shared with humans, be them co-workers, users or clients. It is desirable that these agents adjust to people's preferences, learn faster thanks to their help, and act safely around them. We argue that most current approaches that learn from hu…
Many complex domains, such as robotics control and real-time strategy (RTS) games, require an agent to learn a continuous control. In the former, an agent learns a policy over and in the latter, over a discrete set of actions each of which is parametrized by a continuous parameter. Such problems are natu…
Genetic algorithms have been widely used in many practical optimization problems. Inspired by natural selection, operators, including mutation, crossover and selection, provide effective heuristics for search and black-box optimization. However, they have not been shown useful for deep reinforcement learning, possibly …
Monotonic policy improvement and off-policy learning are two main desirable properties for reinforcement learning algorithms. In this paper, by lower bounding the performance difference of two policies, we show that the monotonic policy improvement is guaranteed from on- and off-policy mixture samples. An optimization …
Representing a dialog policy as a recurrent neural network (RNN) is attractive because it handles partial observability, infers a latent representation of state, and can be optimized with supervised learning (SL) or reinforcement learning (RL). For RL, a policy gradient approach is natural, but is sample inefficient. I…
Hybrid RL algorithm combines offline and online data for robust and efficient policy learning.
problem Combining robust on-policy methods with efficient offline data for hybrid RL.
method Integrates off-policy training on offline data into on-policy NPG framework.
result Achieves state-of-the-art theoretical guarantees and maintains on-policy NPG guarantees.
New RL algorithm tackles non-stationary environments with flexible policy updates.
problem Non-stationary reinforcement learning with time-varying rewards and transition probabilities.
method Model-free policy-based algorithm NS-NAC with restart-based exploration and dynamic learning rates.
result Dynamic regret of for both algorithms.
In this paper we propose a novel gradient algorithm to learn a policy from an expert's observed behavior assuming that the expert behaves optimally with respect to some unknown reward function of a Markovian Decision Problem. The algorithm's aim is to find a reward function such that the resulting optimal policy matche…
Previously, the exploding gradient problem has been explained to be central in deep learning and model-based reinforcement learning, because it causes numerical issues and instability in optimization. Our experiments in model-based reinforcement learning imply that the problem is not just a numerical issue, but it may …
We study reinforcement learning of chatbots with recurrent neural network architectures when the rewards are noisy and expensive to obtain. For instance, a chatbot used in automated customer service support can be scored by quality assurance agents, but this process can be expensive, time consuming and noisy. Previous …
PC-PG balances exploration and exploitation in reinforcement learning.
problem Local policy gradient methods struggle with exploration.
method PC-PG uses an ensemble of learned policies (policy cover) to balance exploration and exploitation.
result PC-PG provides strong theoretical guarantees and empirical validation.
The paper reveals that baselines significantly impact RL algorithms' convergence.
problem Understanding the true impact of baselines on policy optimization.
method Theoretical analysis of bandit and RL problems, focusing on natural policy gradient and EXP3.
result Baselines can determine algorithm convergence, contradicting traditional optimization theory.
Proposes a method to learn policies from offline data with reduced bias.
problem Learning policies from offline data with reduced bias and complexity constraints.
method Cross-fitted debiasing device for policy learning from offline data.
result Achieves regret for complex policy classes with a product-of-errors nuisance remainder.
Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradientcs.LG
Model-free reinforcement learning algorithms such as Deep Deterministic Policy Gradient (DDPG) often require additional exploration strategies, especially if the actor is of deterministic nature. This work evaluates the use of model-based trajectory optimization methods used for exploration in Deep Deterministic Policy…
NM-PPG optimizes adaptive feature acquisition in POMDPs for better predictions.
problem Optimizing adaptive feature acquisition in prediction problems with costly features.
method Non-myopic pathwise policy gradients (NM-PPG) with continuous relaxation and straight-through rollout.
result NM-PPG outperforms state-of-the-art AFA methods on synthetic and real-world datasets.
Study on sample complexity of policy gradient for stabilizing linear systems under multiplicative noise.
problem Learning optimal feedback gain for stabilizing linear systems with multiplicative noise.
method Analyzes the sample complexity of policy gradient methods, addressing the cusp obstruction and using symmetry to control divergent parts of the gradient.
result Proves that projected mini-batch policy gradient attains total sample complexity of O(1/η) when noise density is known and O(η^(-(2s+1)/(2s))) when estimated, for C^s noise densities with s ≥ 2.
Extends RL to random stopping times, improving optimization.
problem Real-world applications with random stopping times.
method Extended RL framework to random stopping times, derived new formulas.
result Improves optimization convergence with new formulas.
Optimizes LLM prompts using logged user feedback.
problem Naive approaches to optimizing LLM prompts suffer from high variance and bias.
method Kernel-based off-policy gradient method leveraging sentence similarity.
result Substantially reduces variance and suppresses bias in optimizing prompts.
This work overcomes bias in concave multi-objective reinforcement learning.
problem Gradient bias in policy gradient methods for concave scalarized multi-objective reinforcement learning.
method Developed a Natural Policy Gradient (NPG) algorithm with a multi-level Monte Carlo (MLMC) estimator.
result Achieved optimal sample complexity for computing an -optimal policy.
We propose a sequential learning policy for noisy discrete global optimization and ranking and selection (R\&S) problems with high dimensional sparse belief functions, where there are hundreds or even thousands of features, but only a small portion of these features contain explanatory power. We aim to identify the spa…
Study Federated RL with diverse constraints, proposing new optimization methods.
problem Solving reinforcement learning with multiple constraints in federated learning.
method Federated primal-dual policy optimization methods based on policy gradient methods.
result FedNPG achieves global convergence with an rate.
On Policy Gradientscs.LG
The goal of policy gradient approaches is to find a policy in a given class of policies which maximizes the expected return. Given a differentiable model of the policy, we want to apply a gradient-ascent technique to reach a local optimum. We mainly use gradient ascent, because it is theoretically well researched. The …
Deep reinforcement learning boosts commodities trading performance.
problem Improving algorithmic trading performance in commodities markets.
method Formulated as a stochastic dynamical system, employed actor-based and actor-critic-based policy gradient algorithms with CNN and LSTM function approximators.
result DRL models increase Sharpe ratio by 83% compared to buy-and-hold.
MAMBA learns policies competitive with multiple conflicting oracles.
problem Learning policies from multiple conflicting oracles in reinforcement learning.
method MAMBA uses a gradient estimator in the style of GAE to optimize policies, leveraging demonstrations from multiple weak oracles.
result MAMBA outperforms the state-of-the-art in learning policies competitive with multiple conflicting oracles.