arXiv research

New methods estimate policy value and gradients for deterministic policies from off-policy data.

Develops DPG methods for continuous-time RL with deterministic policies.

Extends OPE to evaluate policies using diverse logging data.

We study a reinforcement learning setting, where the state transition function is a convex combination of a stochastic continuous function and a deterministic function. Such a setting generalizes the widely-studied stochastic state transition setting, namely the setting of deterministic policy gradient (DPG). We firstl…

Reinforcement learning algorithms such as the deep deterministic policy gradient algorithm (DDPG) has been widely used in continuous control tasks. However, the model-free DDPG algorithm suffers from high sample complexity. In this paper we consider the deterministic value gradients to improve the sample efficiency of …

In the context of learning deterministic policies in continuous domains, we revisit an approach, which was first proposed in Continuous Actor Critic Learning Automaton (CACLA) and later extended in Neural Fitted Actor Critic (NFAC). This approach is based on a policy update different from that of deterministic policy g…

ZDPG learns model-free policies without critics, improving on PG.

Develops a new reinforcement learning framework for complex control problems.

We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected sarsa, EPG integrates across the action when estimating the gradient, instead of relying only on the action in the sampled trajectory. We es…

In this work, we provide theoretical guarantees for reward decomposition in deterministic MDPs. Reward decomposition is a special case of Hierarchical Reinforcement Learning, that allows one to learn many policies in parallel and combine them into a composite solution. Our approach builds on mapping this problem into a…

Reinforcement learning is a promising approach to learning robotics controllers. It has recently been shown that algorithms based on finite-difference estimates of the policy gradient are competitive with algorithms based on the policy gradient theorem. We propose a theoretical framework for understanding this phenomen…

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…

Develops a reinforcement learning algorithm for learning deterministic equilibrium policies in time-inconsistent control problems.

This paper uses deep reinforcement learning to optimize stock portfolios considering transaction costs and risks.

We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected sarsa, EPG integrates (or sums) across actions when estimating the gradient, instead of relying only on the action in the sampled trajectory…

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…

We explore the problem of learning to decompose spatial tasks into segments, as exemplified by the problem of a painting robot covering a large object. Inspired by the ability of classical decision tree algorithms to construct structured partitions of their input spaces, we formulate the problem of decomposing objects …

This paper investigates a type of instability that is linked to the greedy policy improvement in approximated reinforcement learning. We show empirically that non-deterministic policy improvement can stabilize methods like LSPI by controlling the improvements' stochasticity. Additionally we show that a suitable represe…

A novel efficient method for computing the Knowledge-Gradient policy for Continuous Parameters (KGCP) for deterministic optimization is derived. The differences with Expected Improvement (EI), a popular choice for Bayesian optimization of deterministic engineering simulations, are explored. Both policies and the Upper …

Proposes a new policy gradient algorithm to improve reinforcement learning efficiency and stability.

This paper investigates trajectory tracking problem for a class of underactuated autonomous underwater vehicles (AUVs) with unknown dynamics and constrained inputs. Different from existing policy gradient methods which employ single actor-critic but cannot realize satisfactory tracking control accuracy and stable learn…

TT-DAC-PS: A deterministic actor-critic approach for optimal trade execution

Aims to learn from multiple unpredictable teachers with minimal interaction.

Real-world tasks are often highly structured. Hierarchical reinforcement learning (HRL) has attracted research interest as an approach for leveraging the hierarchical structure of a given task in reinforcement learning (RL). However, identifying the hierarchical policy structure that enhances the performance of RL is n…

Extends RL to random stopping times, improving optimization.

New framework for evaluating ad auctions using stochastic modeling.

A deep learning strategy outperforms traditional methods in stocks portfolio management.

This work adopts the very successful distributional perspective on reinforcement learning and adapts it to the continuous control setting. We combine this within a distributed framework for off-policy learning in order to develop what we call the Distributed Distributional Deep Deterministic Policy Gradient algorithm, …

Counterfactual learning is a natural scenario to improve web-based machine translation services by offline learning from feedback logged during user interactions. In order to avoid the risk of showing inferior translations to users, in such scenarios mostly exploration-free deterministic logging policies are in place. …

Deep reinforcement learning (DRL) on Markov decision processes (MDPs) with continuous action spaces is often approached by directly training parametric policies along the direction of estimated policy gradients (PGs). Previous research revealed that the performance of these PG algorithms depends heavily on the bias-var…

New method finds exact Pareto front for MO-MDPs efficiently.

Inter-Cell Interference Coordination (ICIC) is a promising way to improve energy efficiency in wireless networks, especially where small base stations are densely deployed. However, traditional optimization based ICIC schemes suffer from severe performance degradation with complex interference pattern. To address this …

Rate change calculations in the literature involve deterministic methods that measure the change in premium for a given policy. The definition of rate change as a statistical parameter is proposed to address the stochastic nature of the premium charged for a policy. It promotes the idea that rate change is a property o…

Improves pre-trial risk assessments by making them safer without changing existing rules.

Deep neuroevolution and deep reinforcement learning (deep RL) algorithms are two popular approaches to policy search. The former is widely applicable and rather stable, but suffers from low sample efficiency. By contrast, the latter is more sample efficient, but the most sample efficient variants are also rather unstab…

We propose an algorithm for deterministic continuous Markov Decision Processes with sparse rewards that computes the optimal policy exactly with no dependency on the size of the state space. The algorithm has time complexity of $O( |R|^3 \times |A|^2 )$ and memory complexity of $O( |R| \times |A| )$, where $|R|$ is the…

In this paper we consider the basic version of Reinforcement Learning (RL) that involves computing optimal data driven (adaptive) policies for Markovian decision process with unknown transition probabilities. We provide a brief survey of the state of the art of the area and we compare the performance of the classic UCB…

Continuous control imitation learning fails if expert actions are smooth.

FACMAC combines deep policy gradients with factored critic for multi-agent reinforcement learning.

In this paper, we propose a novel meta-learning method in a reinforcement learning setting, based on evolution strategies (ES), exploration in parameter space and deterministic policy gradients. ES methods are easy to parallelize, which is desirable for modern training architectures; however, such methods typically req…

Applying probabilistic models to reinforcement learning (RL) enables the application of powerful optimisation tools such as variational inference to RL. However, existing inference frameworks and their algorithms pose significant challenges for learning optimal policies, e.g., the absence of mode capturing behaviour in…

This note fills the gap in market-consistent valuation of lifelong health insurance products.

In data-limited settings, stochastic policies can outperform deterministic ones in bandit problems.

Improves RL algorithms with two techniques.

SAVO actor improves reinforcement learning by avoiding local optima in complex Q-functions.

This paper compares eight DRL algorithms for dynamic hedging.

Adaptive optimal control of nonlinear dynamic systems with deterministic and known dynamics under a known undiscounted infinite-horizon cost function is investigated. Policy iteration scheme initiated using a stabilizing initial control is analyzed in solving the problem. The convergence of the iterations and the optim…

We observe that several existing policy gradient methods (such as vanilla policy gradient, PPO, A2C) may suffer from overly large gradients when the current policy is close to deterministic (even in some very simple environments), leading to an unstable training process. To address this issue, we propose a new method, …