The paper interprets policy-gradient algorithms using continuation theory.
problem Optimizing nonconvex functions in reinforcement learning.
method Formulates policy optimization as optimization by continuation, interprets policy-gradient algorithms as implicitly optimizing deterministic policies.
result Exploration in policy-gradient algorithms is seen as computing a continuation of the return of the policy.
New algorithm finds near-optimal policies efficiently in zero-sum games.
problem Lack of provable efficiency guarantees for policy optimization in zero-sum games.
method Policy optimization algorithm with function approximation.
result Proves efficient convergence to near-optimal policies with polynomial samples and iterations.
EPIC quantifies reward differences without policy optimization.
problem Distinguishing reward function quality from policy optimization issues.
method EPIC distance to compare reward functions directly.
result EPIC bounds policy training success and regret.
Proposes a Riemannian optimization for policy improvement in MDPs.
problem Optimizing policy functions in Markov decision processes (MDPs).
method Riemannian proximal optimization algorithm with Gaussian mixture model (GMM).
result Guaranteed convergence and efficacy demonstrated in preliminary experiments.
Paper introduces a new value function for state transitions and optimal policy learning.
problem Learning optimal policies from state transitions and actions.
method Develops a forward dynamics model to maximize a novel value function Q(s,s′). result Demonstrates benefits in value function transfer, redundant action spaces, and off-policy learning.
Adapts GRPO for off-policy RL, improving reward.
problem Improving training stability and efficiency in RL.
method Adapts GRPO to off-policy setting, uses clipped surrogate objectives.
result Off-policy GRPO outperforms on-policy GRPO in empirical tests.
Entropy regularization improves policy optimization in reinforcement learning.
problem Improving policy optimization in reinforcement learning.
method Entropy regularization is introduced to soften the greedy policy towards a more diverse softmax policy, leading to a continuously parameterized algorithm that interpolates between policy gradient and Q-learning.
result An intermediate algorithm can improve performance in reinforcement learning.
Temporal difference learning and Residual Gradient methods are the most widely used temporal difference based learning algorithms; however, it has been shown that none of their objective functions is optimal w.r.t approximating the true value function V. Two novel algorithms are proposed to approximate the true value…
PPOS improves PPO by smoothing the surrogate objective function.
problem Performance instability and optimization inefficiency in PPO.
method Use of a functional clipping method instead of a flat clipping method.
result PPOS conducts more accurate updates and outperforms other PPO variants.
This paper optimizes sampling policies for Bayesian optimization to improve exploration and exploitation.
problem Improving the balance between exploration and exploitation in Bayesian optimization.
method Developed efficient methods to estimate and optimize non-myopic acquisition functions using rollout policies and stochastic gradient optimization.
result Efficient optimization of sampling policies leads to better performance in Bayesian optimization.
This paper optimizes off-policy evaluation in reinforcement learning with function approximation.
problem Estimating cumulative value of a new policy from logged data generated by an unknown policy.
method Regression-based fitted Q iteration method, equivalent to estimating conditional mean embedding of transition operator.
result The method is minimax-optimal, with nearly minimal estimation error.
N-discount optimality was introduced as a hierarchical form of policy- and value-function optimality, with Blackwell optimality lying at the top level of the hierarchy Veinott (1969); Blackwell (1962). We formalize notions of myopic discount factors, value functions and policies in terms of Blackwell optimality in MDPs…
Entropy regularization is commonly used to improve policy optimization in reinforcement learning. It is believed to help with \emph{exploration} by encouraging the selection of more stochastic policies. In this work, we analyze this claim using new visualizations of the optimization landscape based on randomly perturbi…
Advocates focusing on utility functions to avoid unfair outcomes.
problem Unfair outcomes from fairness criteria in optimizing policies.
method Defines value of information fairness and proposes modifying utility functions.
result Value of information fairness leads to better answers than existing fairness notions.
Policy gradient converges to globally optimal policy in nearly linear-quadratic systems.
problem Finding optimal policies in nonlinear control systems with partial information.
method Policy gradient algorithm designed for nearly linear-quadratic regulators with small Lipschitz nonlinear components.
result Policy gradient algorithm converges to globally optimal policy with linear rate.
Managers of US National Forests must decide what policy to apply for dealing with lightning-caused wildfires. Conflicts among stakeholders (e.g., timber companies, home owners, and wildlife biologists) have often led to spirited political debates and even violent eco-terrorism. One way to transform these conflicts into…
Paper optimizes traffic signal control for better traffic flow.
problem Optimizing traffic signal control to reduce congestion and improve safety.
method Value-based reinforcement learning with interpretable policy functions (polynomial functions).
result Deep Regulatable Hardmax Q-learning variant reduces vehicle delay by up to 19.4%.
ENIAC method optimizes and explores complex RL problems with non-linear policies.
problem Theoretical understanding of non-linear policies in RL with strategic exploration.
method ENIAC, an actor-critic method for non-linear function approximation.
result ENIAC finds near-optimal policies in polynomial exploration rounds under bounded eluder dimension.
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 f-divergence-constrained reward maximization problem, learning policies directly. result Induces a semiparametric single-index binary choice model for policy alignment.
PROPO tackles non-stationary MDPs with efficient policy optimization.
problem Non-stationary MDPs with varying reward and transition kernels.
method PROPO, a periodic restarted optimistic policy optimization algorithm with sliding-window-based policy evaluation and improvement.
result PROPO achieves near-optimal performance in non-stationary MDPs.
We consider off-policy evaluation and optimization with continuous action spaces. We focus on observational data where the data collection policy is unknown and needs to be estimated. We take a semi-parametric approach where the value function takes a known parametric form in the treatment, but we are agnostic on how i…
We accelerate PMD algorithms for reinforcement learning using functional methods.
problem Improving reinforcement learning algorithms for large-scale optimization.
method Proposed a momentum-based update for PMD algorithms leveraging duality.
result The proposed method accelerates reinforcement learning algorithms.
We compare the model-free reinforcement learning with the model-based approaches through the lens of the expressive power of neural networks for policies, Q-functions, and dynamics. We show, theoretically and empirically, that even for one-dimensional continuous state space, there are many MDPs whose optimal Q-func…
PPO algorithm converges to global optimality in multi-agent reinforcement learning.
problem Designing statistical guarantees for policy optimization methods in multi-agent reinforcement learning.
method Leveraging a multi-agent performance difference lemma, a localized action value function is used as a descent direction for each local policy, leading to a multi-agent PPO algorithm.
result The multi-agent PPO algorithm converges to the globally optimal policy at a sublinear rate under standard regularity conditions.
Single-timescale actor-critic finds globally optimal policy.
problem Finding globally optimal policy in reinforcement learning.
method Simultaneous actor and critic updates with linear or deep neural network approximations.
result Actor sequence converges to globally optimal policy at O(K−1/2) rate. New method estimates and optimizes policy differences using orthogonal learning.
problem Offline reinforcement learning with safety concerns and cost limitations.
method Dynamic R-learner for estimating and optimizing Qπ(s,1)−Qπ(s,0), leveraging orthogonal estimation. result Consistent policy optimization with improved convergence rates.
We study the safe reinforcement learning problem with nonlinear function approximation, where policy optimization is formulated as a constrained optimization problem with both the objective and the constraint being nonconvex functions. For such a problem, we construct a sequence of surrogate convex constrained optimiza…
Discuss new policy learning objectives and methods.
problem Improving policy learning efficiency and robustness.
method Introducing curvature considerations and calibration data methods.
result Efficient retargeting and distributionally robust policies.
PPG separates policy and value function training phases for better reinforcement learning efficiency.
problem Challenges in traditional reinforcement learning methods for policy and value function optimization.
method Integrates Phasic Policy Gradient framework that splits policy and value function training into distinct phases.
result Significantly improves sample efficiency on Procgen Benchmark compared to PPO.
ZSPO optimizes RL from unknown link functions using human feedback.
problem Designing RLHF algorithms for unknown link functions.
method Zero-order policy optimization with human preference feedback.
result ZSPO converges to a stationary policy with a polynomial rate.
A key problem in reinforcement learning for control with general function approximators (such as deep neural networks and other nonlinear functions) is that, for many algorithms employed in practice, updates to the policy or Q-function may fail to improve performance---or worse, actually cause the policy performance …
New method learns optimal policies in presence of unmeasured confounders.
problem Optimal policy learning with unobserved confounders.
method Causal-assisted policy learning methods using instrumental variables and negative controls.
result Policies are ildeO(n−1/2) quantile-optimal under mild coverage assumptions. Bayesian Robust Optimization for Imitation Learning (BROIL) balances risk and reward.
problem Learning robust policies for new states in imitation learning.
method Bayesian reward function inference and user-specific risk tolerance.
result BROIL outperforms risk-sensitive and risk-neutral algorithms.
Policy optimization is an effective reinforcement learning approach to solve continuous control tasks. Recent achievements have shown that alternating online and offline optimization is a successful choice for efficient trajectory reuse. However, deciding when to stop optimizing and collect new trajectories is non-triv…
Stabilizes policy optimization with off-policy data using divergence augmentation.
problem Premature convergence and instability in policy optimization with off-policy data.
method Incorporates Bregman divergence between behavior and current policies to ensure safe policy updates.
result Empirically shows better performance in data-scarce scenarios compared to other algorithms.
In this paper, we propose a distributed off-policy actor critic method to solve multi-agent reinforcement learning problems. Specifically, we assume that all agents keep local estimates of the global optimal policy parameter and update their local value function estimates independently. Then, we introduce an additional…
The paper analyzes optimal liquidation strategies for cryptocurrencies considering both temporary and permanent price impacts.
problem Optimal liquidation strategies for cryptocurrencies in the presence of price impacts.
method Analytical and numerical solutions, including finite differences and optimal policy iteration.
result Optimal liquidation policies vary based on the functional form of temporary and permanent price impacts.
We consider a version of the stochastic inventory control problem for a spectrally positive Lévy demand process, in which the inventory can only be replenished at independent exponential times. We show the optimality of a periodic barrier replenishment policy that restocks any shortage below a certain threshold at each…
Optimizes Thompson sampling policies using policy gradient methods.
problem Improving Thompson sampling in bandit problems.
method Applies policy gradient algorithms to optimize Thompson sampling policies.
result Direct policy search on Thompson sampling improves performance.
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.
A new method improves policy evaluation in RL by tracking value uncertainties.
problem Limitations in existing policy evaluation methods for deep RL tasks.
method KOVA (Kalman Optimization for Value Approximation) based on extended Kalman filter.
result KOVA minimizes a regularized objective function that considers parameter and noisy return uncertainties.
Proposes a new reinforcement learning algorithm using Q-function.
problem Optimal control in Markov Decision Processes (MDPs).
method Regularized linear-programming formulation, Q-function, saddle-point optimization.
result Demonstrates effectiveness on various benchmark problems.
This paper optimizes MDP policies for efficient state aggregation.
problem Optimizing policies in aggregated Markov chains while preserving optimal performance.
method Homomorphic mappings to establish optimal policy equivalence and derive performance bounds.
result Developed HPG and EBHPG methods for efficient aggregation and policy optimization.
New method efficiently evaluates policies using trajectory data.
problem Statistically efficient policy evaluation with limited data.
method Trajectory-based approach for policy evaluation.
result Improved sample complexity for policy evaluation.
DR-RPO optimizes robust policies in RL with limited interaction, achieving sublinear regret.
problem Policy optimization in RL under distribution shift and adversarial dynamics.
method DR-RPO algorithm incorporating reference-policy regularization and upper confidence bonus for exploration.
result DR-RPO achieves sublinear regret and polynomial suboptimality bounds in robust RL.
This paper optimizes slate decision systems for large action spaces.
problem Optimizing large-scale decision systems with arbitrary reward functions.
method A policy optimization framework with a novel relaxation of decision functions.
result Demonstrates the effectiveness of the proposed method on large action spaces.
Unified minimax value interval for off-policy evaluation and optimization.
problem Overcoming the exponential variance in off-policy evaluation and policy optimization.
method Unified minimax value interval using marginalized importance weights.
result Unified value interval with double robustness, valid when either value-function or importance-weight class is well specified.
Efficiently reduces computational burden of rollout acquisition functions in Bayesian optimization.
problem Expensive computation of rollout acquisition functions in Bayesian optimization.
method Combines quasi-Monte Carlo, common random numbers, and control variates to reduce computational burden. Formulates a policy-search approach to eliminate the need to optimize the rollout acquisition function.
result Significant reduction in computational burden of rollout acquisition functions.