A core novelty of Alpha Zero is the interleaving of tree search and deep learning, which has proven very successful in board games like Chess, Shogi and Go. These games have a discrete action space. However, many real-world reinforcement learning domains have continuous action spaces, for example in robotic control, na…
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.
168,932 papers · 148 categories
Trend · papers per month
48 results for “Continuous-Action Tasks”
Enhances SAC for better sample efficiency in continuous-action tasks.
problem Improving sample efficiency in soft actor-critic algorithms.
method Integrating Emphasizing Recent Experience (ERE) with Soft Actor-Critic (SAC) and Priority Experience Replay (PER).
result ERE significantly improves sample efficiency compared to vanilla SAC, especially for continuous-action tasks.
Hybrid SAC improves RL for video games with discrete, continuous actions.
problem Improving RL performance in video games with practical constraints.
method Extension of Soft Actor-Critic (SAC) for handling discrete, continuous, and parameterized actions.
result Hybrid SAC successfully solves a high-speed driving task and is competitive on parameterized actions benchmarks.
We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain. We present an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces. Using the same learning algorithm, network architecture and hyper-parameters, our algo…
New algorithm for context bandits with continuous actions.
problem Efficient decision-making with unknown action structures.
method Reduction-style algorithm combining supervised learning.
result Proven to work in general and validated with experiments.
Most reinforcement learning algorithms are inefficient for learning multiple tasks in complex robotic systems, where different tasks share a set of actions. In such environments a compound policy may be learnt with shared neural network parameters, which performs multiple tasks concurrently. However such compound polic…
SDPG algorithm improves sample efficiency and reward in DRL for continuous action spaces.
problem Improving sample efficiency and reward in distributional reinforcement learning for continuous action spaces.
method SDPG algorithm models return distribution using samples via reparameterization technique.
result SDPG shows better sample efficiency and higher reward in OpenAI Gym environments.
CAQL tackles continuous action maximization in Q-learning.
problem Maximizing continuous actions in Q-learning.
method Developed CAQL algorithms using plug-and-play optimizers and MIP for optimal max-Q.
result CAQL outperforms policy-based methods in heavily constrained environments.
QAM uses adjoint matching to optimize continuous-action RL policies efficiently.
problem Efficient optimization of expressive diffusion or flow-matching policies with respect to a Q-function.
method QAM leverages adjoint matching to bypass the numerical instability of backpropagation through multi-step denoising processes.
result QAM consistently outperforms prior approaches on hard, sparse reward tasks in offline and offline-to-online RL.
The paper tackles counterfactual learning for stochastic policies with continuous actions.
problem Learning stochastic policies with continuous actions from logged data.
method Introduces a joint kernel embedding of contexts and actions to model continuous actions, and uses proximal point algorithms and smooth estimators for optimization.
result Demonstrates the benefits of using proximal point algorithms and smooth estimators for counterfactual learning.
Paper proposes interpretable RL policies from a mixture of experts.
problem Making RL policies transparent and understandable in real-world applications.
method Policy iteration scheme with interpretable experts and prototypical states.
result Proposed algorithm learns policies comparable to neural networks but more interpretable.
Reliable and effective multi-task learning is a prerequisite for the development of robotic agents that can quickly learn to accomplish related, everyday tasks. However, in the reinforcement learning domain, multi-task learning has not exhibited the same level of success as in other domains, such as computer vision. In…
The paper proposes a method to learn continuous-action graphical games from perturbed equilibria.
problem Learning the exact structure of continuous-action graphical games from limited data.
method A block regularized method to recover the graphical game structure.
result The method recovers the exact structure of the graphical game under certain conditions.
A new method for RL with continuous actions improves stability and scalability.
problem Stability and scalability issues in existing RL methods.
method Soft policy gradient with entropy regularization, combined with double sampling for soft Bellman equation.
result Outperforms off-policy prior methods in continuous action RL tasks.
The paper proposes a method to learn the structure of continuous-action games with non-parametric utilities using a limited number of samples.
problem Learning the exact structure of continuous-action games with non-parametric utility functions.
method An regularized method that encourages sparsity of the Fourier transform coefficients of the utility functions, accessed via a few Nash equilibria and their noisy utilities.
result The method recovers the exact structure of the utility functions and the game structure with provable theoretical guarantees.
Paper tackles RL with continuous actions and unmeasured confounders.
problem Offline policy learning with continuous actions and unmeasured confounders.
method Developed a novel identification result and a minimax estimator for nonparametric policy value estimation.
result Introduced a policy-gradient-based algorithm to identify the optimal policy.
Any continuous action of SL(n,Z), where n > 2, on a r-dimensional mod 2 homology sphere factors through a finite group action if r < n - 1. In particular, any continuous action of SL(n+2,Z) on the n-dimensional sphere factors through a finite group action.
Develops a statistical learning framework for personalized asset allocation.
problem Continuous-action decision-making with a large number of characteristics.
method Discretization approach with generalized penalties for penalized regression.
result Improves financial well-being with individualized optimal asset allocation.
Efficient algorithms for contextual bandits with smooth regret in continuous action spaces.
problem Efficient learning in large or continuous action spaces.
method Smooth regret notion and efficient algorithms for general function approximation.
result Statistically and computationally efficient algorithms for contextual bandits with smooth regret.
A Game of Competition for Riskq-fin.CP
Models analyze strategic risk-taking in continuous action games.
problem Strategic risk-taking dynamics in continuous action games.
method Normal form game, multi-player scenarios, regret minimization algorithms, numerical algorithm for calculation.
result Nash equilibrium also serves as a correlated equilibrium in continuous games.
New method extends low-rank MDPs to continuous action spaces.
problem Limited applicability of current low-rank MDP methods to continuous action spaces.
method Extending FLAMBE algorithm to continuous action spaces with Hölder smoothness conditions.
result Similar PAC bound achieved for continuous actions with polynomial dependence on smoothness order.
We study contextual bandit learning with an abstract policy class and continuous action space. We obtain two qualitatively different regret bounds: one competes with a smoothed version of the policy class under no continuity assumptions, while the other requires standard Lipschitz assumptions. Both bounds exhibit data-…
Develops a new RL algorithm for medical treatment regimes.
problem Optimal dose determination in continuous action environments.
method Quasi-optimal learning algorithm for near-optimal actions.
result Guaranteed convergence and effectiveness in real applications.
Hybrid Policy Optimization tackles reinforcement learning in hybrid spaces, improving performance over PPO.
problem Credit assignment issues and biased gradients in hybrid discrete-continuous action spaces.
method Mixed gradient estimator combining pathwise and score-function gradients, reformulating problems in hybrid form.
result HPO substantially outperforms PPO on inventory control and switched systems, with performance gaps increasing with continuous action dimension.
In this article, we sketch an algorithm that extends the Q-learning algorithms to the continuous action space domain. Our method is based on the discretization of the action space. Despite the commonly used discretization methods, our method does not increase the discretized problem dimensionality exponentially. We wil…
We show that every continuous action of a finite group on a smooth three-manifold is a uniform limit of smooth actions.
RL agent learns to smoothly change lanes in a dynamic driving environment.
problem Challenging lane change control with safety and comfort.
method Formulated continuous action for lane change in DDPG algorithm, defined reward function for learning.
result Successfully changed lanes with 100% success rate in diverse driving situations.
The paper explores properties of continuous actions on manifolds, proving bounds on subgroup size and fixed points.
problem Properties of continuous finite group actions on topological manifolds.
method Analyzes properties including Jordan property and almost fixed point property, proving bounds on subgroup size.
result Existence of a constant C such that for any continuous action of a finite group G on a manifold X, there is a subgroup H with [G:H] ≤ C and a fixed point.
Multiagent reinforcement learning algorithms (MARL) have been demonstrated on complex tasks that require the coordination of a team of multiple agents to complete. Existing works have focused on sharing information between agents via centralized critics to stabilize learning or through communication to increase perform…
Many real world tasks exhibit rich structure that is repeated across different parts of the state space or in time. In this work we study the possibility of leveraging such repeated structure to speed up and regularize learning. We start from the KL regularized expected reward objective which introduces an additional c…
New STDP rule for spiking neurons solves discrete action reinforcement learning tasks.
problem Applying standard STDP to discrete action reinforcement learning tasks.
method Feedback-modulated TD-STDP learning rule for spiking neuron networks.
result Feedback modulation improves credit assignment in reinforcement learning.
Composing previously mastered skills to solve novel tasks promises dramatic improvements in the data efficiency of reinforcement learning. Here, we analyze two recent works composing behaviors represented in the form of action-value functions and show that they perform poorly in some situations. As part of this analysi…
Reinforcement learning algorithms are gaining popularity in fields in which optimal scheduling is important, and oncology is not an exception. The complex and uncertain dynamics of cancer limit the performance of traditional model-based scheduling strategies like Optimal Control. Motivated by the recent success of mode…
We propose a new sample-efficient methodology, called Supervised Policy Update (SPU), for deep reinforcement learning. Starting with data generated by the current policy, SPU formulates and solves a constrained optimization problem in the non-parameterized proximal policy space. Using supervised regression, it then con…
Most existing deep reinforcement learning (DRL) frameworks consider either discrete action space or continuous action space solely. Motivated by applications in computer games, we consider the scenario with discrete-continuous hybrid action space. To handle hybrid action space, previous works either approximate the hyb…
PTF accelerates RL by reusing source policies without measuring task similarity.
problem Leveraging prior knowledge for faster RL.
method Adaptive Policy Transfer Framework (PTF) for RL.
result Significantly accelerates RL learning process and surpasses state-of-the-art methods.
New metric for off-policy evaluation without models or importance sampling.
problem Evaluating deep RL models in real-world environments is costly and impractical.
method Framed as a PU classification problem, using Q-function as decision function.
result Metric reliably predicts policy performance in various scenarios.
Study compares SPG and PPO for racing games, finding SPG more stable with weighted actions.
problem Training continuous action reinforcement learning algorithms for racing games.
method Introduced novel racing environment, tested SPG and PPO with modifications and experience replay.
result Experience replay not beneficial for PPO in continuous action spaces, SPG more stable with weighted actions.
Policy Prediction Network improves continuous control problems with model-free and model-based learning.
problem Improving sample complexity and performance in continuous control problems.
method Integrates model-free and model-based reinforcement learning, introduces implicit model-based learning for continuous action space.
result First to introduce implicit model-based learning to Policy Gradient algorithms for continuous action space.
Motivated by the recent applications of game-theoretical learning techniques to the design of distributed control systems, we study a class of control problems that can be formulated as potential games with continuous action sets, and we propose an actor-critic reinforcement learning algorithm that provably converges t…
Proximal Policy Optimization (PPO) is a highly popular model-free reinforcement learning (RL) approach. However, we observe that in a continuous action space, PPO can prematurely shrink the exploration variance, which leads to slow progress and may make the algorithm prone to getting stuck in local optima. Drawing insp…
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…
New method combines value function decomposition and policy gradients for cooperative multi-agent reinforcement learning.
problem Challenges in cooperative multi-agent reinforcement learning, especially credit assignment and large action spaces.
method Decomposed Soft Actor-Critic (mSAC) method with Q network architecture, discrete probabilistic policy, and counterfactual advantage function.
result Significantly outperforms policy-based approach COMA and achieves competitive results with SOTA value-based approach Qmix.
DreamerV2 learns Atari game behaviors from a world model, achieving human-level performance.
problem Learning complex behaviors in Atari games from limited data.
method DreamerV2 uses a world model with discrete representations to predict behaviors in a compact latent space.
result Achieves human-level performance on 55 Atari tasks.
Deep reinforcement learning enables algorithms to learn complex behavior, deal with continuous action spaces and find good strategies in environments with high dimensional state spaces. With deep reinforcement learning being an active area of research and many concurrent inventions, we decided to focus on a relatively …
Despite increasing attention paid to the need for fast, scalable methods to analyze next-generation neuroscience data, comparatively little attention has been paid to the development of similar methods for behavioral analysis. Just as the volume and complexity of brain data have grown, behavioral paradigms in systems n…
AQL uses amortized inference to handle high-dimensional action spaces in Q-learning.
problem Difficulty in maximizing over large action spaces in Q-learning.
method Replace expensive maximization over all actions with a maximization over a small subset sampled from a learned proposal distribution.
result AQL outperforms existing methods on continuous control tasks with up to 21 dimensional actions.
Improved exploration in SAC using Normalizing Flows policies.
problem Brittleness and inefficiency of DRL algorithms in continuous action spaces.
method Introducing Normalizing Flow policies within the SAC framework to learn more expressive policies.
result Increased stability and better exploration in sparse reward settings.