In quadruped gait learning, policy search methods that scale high dimensional continuous action spaces are commonly used. In most approaches, it is necessary to introduce prior knowledge on the gaits to limit the highly non-convex search space of the policies. In this work, we propose a new approach to encode the symme…
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.
168,878 papers · 148 categories
Trend · papers per month
48 results for “relative entropy policy search”
Direct contextual policy search methods learn to improve policy parameters and simultaneously generalize these parameters to different context or task variables. However, learning from high-dimensional context variables, such as camera images, is still a prominent problem in many real-world tasks. A naive application o…
Paper proposes a policy-search algorithm to learn entropy-maximizing exploration policies in reward-free environments.
problem Reward-free learning in high-dimensional, continuous-control domains.
method Maximum Entropy POLicy optimization (MEPOL) algorithm that maximizes a non-parametric state entropy estimate.
result MEPOL learns a maximum-entropy exploration policy that facilitates learning various reward-based tasks.
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…
Robotics learns new skills faster by reusing past movements.
problem Learning new motor skills is time-consuming and requires exploration of a large space of motor configurations.
method Combines probabilistic movement primitives with relative entropy policy search for skill initialization and adaptation.
result Quality of learned skills improves and the number of required iterations to learn a new task can be reduced by more than 60%.
Contextual policy search allows adapting robotic movement primitives to different situations. For instance, a locomotion primitive might be adapted to different terrain inclinations or desired walking speeds. Such an adaptation is often achievable by modifying a small number of hyperparameters. However, learning, when …
Regret-Aware Black-Box Optimization with Natural Gradients, Trust-Regions and Entropy Controlstat.ML
Improved MORE algorithm reduces regret in black-box optimization and RL tasks.
problem Noisy fitness evaluations and poor sample quality in black-box optimization.
method Decouples mean and covariance updates, uses entropy scheduling, and simplifies model learning.
result Significantly reduces regret in black-box optimization and RL tasks.
SymCircuit learns PC structure via entropy-regularized RL, improving inference efficiency and accuracy.
problem Greedy algorithms in PC structure learning lead to suboptimal solutions.
method Entropy-regularized reinforcement learning to train a learned generative policy for PC structure inference.
result SymCircuit learns the optimal policy as a tempered Bayesian posterior, improving inference efficiency and accuracy.
Improves neural network search in combinatorial spaces of mathematical symbols.
problem Early commitment and initialization bias limit exploration in neural network search.
method Entropy regularization and distribution initialization methods.
result Improves performance, increases sample efficiency, lowers solution complexity.
Logistic Q-Learningcs.LG
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.
DE-QT detects optimal Q-learning stopping points.
problem Information loss in Q-learning during prolonged training.
method Introducing DE-QT to detect entropy changes in Q-tables.
result DE-QT identifies the best stopping point for Q-learning.
Methods for learning to search for structured prediction typically imitate a reference policy, with existing theoretical guarantees demonstrating low regret compared to that reference. This is unsatisfactory in many applications where the reference policy is suboptimal and the goal of learning is to improve upon it. Ca…
Framework uses optimal transport for neural architecture search.
problem Optimizing neural architectures in deep learning.
method Semi-discrete optimization using optimal transport.
result Gradient flow and minimizing movement scheme converge to reaction-diffusion equations.
This work extends ME-RL using diffusion models to sample optimal policies.
problem Sampling from the optimal policy trajectory distribution in ME-RL.
method Introducing Diffusion-Augmented Markov Decision Processes (DA-MDPs) to minimize reverse KL divergence.
result DA-MDPs enable seamless integration into various ME-RL methods and outperform baselines.
We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value function. The result is a simple procedure consisting of three steps: i) policy evaluation by estimating a parametric action-value function;…
Paper introduces a new method for risk-sensitive investment management using RL.
problem Risk-sensitive portfolio management with unknown model parameters.
method Combines RL and risk-sensitive stochastic control with Gaussian perturbations for exploration.
result Endogenous relative-entropy regularization and optimal investment strategy derived.
New RL approach uses future state and action visitation measures for better exploration.
problem Improving exploration in reinforcement learning.
method Intrinsic reward based on future state and action visitation measures, using contraction operators.
result Policies achieve good state-action space coverage and high performance.
Fast AutoAugmentcs.LG
Data augmentation is an essential technique for improving generalization ability of deep learning models. Recently, AutoAugment has been proposed as an algorithm to automatically search for augmentation policies from a dataset and has significantly enhanced performances on many image recognition tasks. However, its sea…
In recent years, state-of-the-art game-playing agents often involve policies that are trained in self-playing processes where Monte Carlo tree search (MCTS) algorithms and trained policies iteratively improve each other. The strongest results have been obtained when policies are trained to mimic the search behaviour of…
InfoTree improves reinforcement learning by optimizing tool use with a greedy submodular approach.
problem Maximizing information from tool use in reinforcement learning with limited resources.
method Formalizes Rollout Informativeness, recasts state selection as submodular maximization, and uses UUCB and ABA.
result InfoTree outperforms existing methods across various benchmarks, improving performance by 18.2% on average.
We introduce a new algorithm for reinforcement learning called Maximum aposteriori Policy Optimisation (MPO) based on coordinate ascent on a relative entropy objective. We show that several existing methods can directly be related to our derivation. We develop two off-policy algorithms and demonstrate that they are com…
Mean Actor Criticstat.ML
We propose a new algorithm, Mean Actor-Critic (MAC), for discrete-action continuous-state reinforcement learning. MAC is a policy gradient algorithm that uses the agent's explicit representation of all action values to estimate the gradient of the policy, rather than using only the actions that were actually executed. …
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…
VES-Gamma adapts EI using information-theoretic principles.
problem Optimizing black-box functions using Bayesian optimization.
method Variational Entropy Search (VES) and VES-Gamma algorithm.
result VES-Gamma improves EI by incorporating information-theoretic concepts.
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.
JES optimizes expensive functions by considering joint entropy over input and output spaces.
problem Optimizing expensive functions with limited evaluations.
method Joint Entropy Search (JES) considers joint entropy over input and output spaces.
result JES outperforms other information-theoretic methods in Bayesian optimization.
Entropy Search (ES) and Predictive Entropy Search (PES) are popular and empirically successful Bayesian Optimization techniques. Both rely on a compelling information-theoretic motivation, and maximize the information gained about the of the unknown function; yet, both are plagued by the expensive computatio…
DAC enhances exploration in reinforcement learning with entropy regularization.
problem Improving exploration efficiency in reinforcement learning.
method Sample-aware entropy regularization using replay buffer action distributions.
result DAC significantly outperforms existing algorithms in reinforcement learning tasks.
Study on relative entropy for hypersurfaces in hyperbolic space.
problem Understanding relative entropy for hypersurfaces in hyperbolic space.
method Relate relative entropy to renormalized area and apply monotonicity formula to mean curvature flows.
result Obtained a monotonicity formula for relative entropy in hyperbolic space.
A new algorithm learns diverse policies in reinforcement learning.
problem Learning diverse behaviors in reinforcement learning.
method Proposes Maximum Entropy Diverse Exploration (MEDE) algorithm.
result The set of policies learned by MEDE capture the same modalities as the optimal maximum entropy policy.
Learning Optimal Data Augmentation Policies via Bayesian Optimization for Image Classification Taskscs.LG
In recent years, deep learning has achieved remarkable achievements in many fields, including computer vision, natural language processing, speech recognition and others. Adequate training data is the key to ensure the effectiveness of the deep models. However, obtaining valid data requires a lot of time and labor reso…
New reinforcement learning algorithms improve policy optimization with entropy regularization.
problem Improving policy optimization in reinforcement learning.
method Soft policy gradient theorem (SPGT) and new policy optimization algorithms.
result New algorithms outperform prior works on various benchmark tasks.
CAGES: Cost-Aware Gradient Entropy Search for Efficient Local Multi-Fidelity Bayesian Optimizationcs.LG
CAGES optimizes expensive RL problems by efficiently learning gradients from multiple sources.
problem Optimizing expensive-to-evaluate functions in high-dimensional spaces.
method Cost-Aware Gradient Entropy Search (CAGES) for multi-fidelity Bayesian optimization.
result Significant performance improvements on synthetic and RL benchmark problems.
This work improves policy optimization by maximizing entropy of state distribution, leading to better exploration.
problem Lack of exploration in state space when maximizing policy entropy.
method Proposes maximizing the entropy of a lower bound approximation to the state weighting distribution, based on latent space representation.
result Entropy regularization based on marginal state distribution achieves superior state space coverage and better performance in various domains.
New approach to portfolio optimization shows entropy regularization is ineffective.
problem Entropy regularization in mean-variance portfolio optimization under drift uncertainty.
method Combining Bayesian filtering and stochastic policy optimization.
result Entropy regularization does not accelerate learning about unknown drift.
Enhances RL by controlling policy stochasticity through trajectory entropy constraints.
problem Non-stationary Q-value estimation and short-sighted entropy tuning in maximum entropy RL.
method Proposes TECRL framework with separate Q-functions for reward and entropy, enforcing a trajectory entropy constraint.
result DSAC-E algorithm achieves higher returns and better stability on OpenAI Gym benchmarks.
We introduce Implicit Policy, a general class of expressive policies that can flexibly represent complex action distributions in reinforcement learning, with efficient algorithms to compute entropy regularized policy gradients. We empirically show that, despite its simplicity in implementation, entropy regularization c…
Bayesian Markowitz portfolio problem shows entropy regularization is ineffective.
problem Entropy regularization in Bayesian Markowitz portfolio optimization.
method Combines continuous-time Bayesian filtering with stochastic policy optimization.
result Entropy regularization does not accelerate learning of unknown drift.
Monte Carlo Tree Search (MCTS) algorithms perform simulation-based search to improve policies online. During search, the simulation policy is adapted to explore the most promising lines of play. MCTS has been used by state-of-the-art programs for many problems, however a disadvantage to MCTS is that it estimates the va…
Extends specific relative entropy to multidimensional continuous martingales.
problem Mutual singularity of martingale laws in continuous time.
method Extension of specific relative entropy from one to multiple dimensions, including closed-form expressions for simple examples.
result Establishes that the lower bound on specific relative entropy from Gantert carries over to higher dimensions and is tight.
Evolutionary Strategies optimize hyper-parameters for off-policy learning.
problem Hyper-parameter sensitivity in off-policy learning.
method Application of Evolutionary Strategies for online hyper-parameter tuning.
result Our method outperforms state-of-the-art baselines.
The scientific method relies on the iterated processes of inference and inquiry. The inference phase consists of selecting the most probable models based on the available data; whereas the inquiry phase consists of using what is known about the models to select the most relevant experiment. Optimizing inquiry involves …
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.
Entropy asymmetry affects regularization in ERM, leading to biased solutions.
problem Analyzing the impact of relative entropy asymmetry in ERM regularization.
method Examined Type-I and Type-II ERM-RER, comparing their solutions and properties.
result Type-II ERM-RER regularization introduces a strong bias against training data.
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.
Relative cluster entropy for power-law correlated sequencescond-mat.stat-mech
A measure called relative cluster entropy distinguishes between correlated and uncorrelated sequences.
problem Distinguishing between sequences with different correlation degrees.
method Minimum relative entropy principle applied to cluster partitions of power-law correlated sequences.
result Optimal Hurst exponents are selected for market price series, indicating non-markovianity.
Unified framework connects EI and information-theoretic acquisition functions.
problem Distinguish between Expected Improvement and information-theoretic acquisition functions.
method Introduces Variational Entropy Search (VES) to unify EI and information-theoretic approaches.
result EI can be seen as a variational inference approximation of Max-value Entropy Search (MES).
A new method for constrained Bayesian optimization using Max-Value Entropy Search.
problem Optimizing expensive functions with unknown constraints.
method Constrained Max-value Entropy Search (cMES), a novel acquisition function.
result cMES outperforms prior work on constrained hyperparameter optimization problems.