Study evaluates task selection policies for multitask learning.
problem How to allocate training resources among multiple tasks.
method Empirical evaluation of task selection policies in synthetic and real-world settings.
result Improved model performance through counterfactual estimation.
Robust Policy Search is the problem of learning policies that do not degrade in performance when subject to unseen environment model parameters. It is particularly relevant for transferring policies learned in a simulation environment to the real world. Several existing approaches involve sampling large batches of traj…
Benchmarking off-policy evaluation methods for complex policies.
problem Lack of comprehensive benchmarks for off-policy evaluation methods.
method Collection of challenging high-dimensional control tasks and datasets.
result Standardized measure of progress for OPE methods.
Proposes a Quasi-Newton trust region method for policy optimization in reinforcement learning.
problem Lack of stepsize selection criterion and slow convergence in gradient descent for policy optimization.
method Uses a trust region method with Quasi-Newton approximation for the Hessian.
result Demonstrates improved performance and efficiency in continuous control tasks.
Unified pair trading approach using hierarchical reinforcement learning.
problem Decoupling pair selection and trading leads to limited performance.
method Hierarchical reinforcement learning framework for joint pair selection and trading.
result Unified approach outperforms existing methods on real-world stock data.
New method selects best offline RL policies from logged data.
problem Hyperparameter selection challenges offline RL.
method Offline hyperparameter selection for RL algorithms.
result Reliable ranking and selection of policies across hyperparameters.
Graph Denoising Policy Network learns robust representations from noisy graphs.
problem Noise sensitivity in graph representation learning.
method Reinforcement learning to select signal neighborhoods and aggregate features.
result Significantly outperforms state-of-the-art methods on node classification tasks.
This paper formalises the problem of online algorithm selection in the context of Reinforcement Learning. The setup is as follows: given an episodic task and a finite number of off-policy RL algorithms, a meta-algorithm has to decide which RL algorithm is in control during the next episode so as to maximize the expecte…
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 …
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.
OPERA blends multiple OPE estimators to evaluate new policies offline.
problem Lack of reliable offline policy evaluation methods for new policies.
method Adaptive blending of multiple OPE estimators without explicit selection.
result Consistent and reliable policy evaluation framework for offline RL.
AES improves policy gradient performance by adaptively selecting experience.
problem High variance in gradient estimators from past trajectories.
method AES learns an adaptive sampling distribution to minimise gradient variance.
result AES leads to significantly improved performance in continuous control tasks.
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…
Pipeline selects best RL policy from limited data.
problem Selecting best RL policy from small datasets.
method Task- and method-agnostic pipeline using multiple data splits.
result Pipeline produces higher-performing policies.
New Bellman error estimator improves offline model selection performance.
problem Selecting the best policy from logged data using mean squared Bellman error.
method Developed a more accurate estimator of MSBE and analyzed conditions for successful OMS.
result New estimator achieves impressive offline model selection performance on diverse tasks.
Soft modularization improves sample efficiency and performance in reinforcement learning.
problem Challenges in training multiple tasks jointly in reinforcement learning.
method Explicit modularization technique on policy representation, soft modularization method.
result Improves sample efficiency and performance over strong baselines in robotics manipulation tasks.
We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised, fully-differentiable sequence segmentation module to learn latent encodings of sequential d…
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.
SEERL uses ensemble methods to improve reinforcement learning efficiency.
problem High sample complexity and computational expense in reinforcement learning.
method Directed perturbation of model parameters to learn diverse policies, selection of an adequately diverse set of policies.
result Our approach outperforms state-of-the-art scores in Atari 2600 and Mujoco.
A method for a single policy to solve various tasks across diverse agent morphologies.
problem Generalizing a single policy to solve various tasks across diverse agent morphologies.
method Unified representation and behavior distillation using a morphology-task graph and Transformer architecture.
result Improves multi-task performances compared to baselines, suggesting a promising approach.
Robust HVA adjusts deep hedging policies for market frictions and transaction costs.
problem Ensuring deep hedging policies are financially feasible under market frictions and transaction costs.
method Applying a robust hedging valuation adjustment (HVA) post-training to evaluate and adjust policies for funding and margin add-ons.
result A single HVA computation provides a consistent reserve for funding and margin, improving financial feasibility of deep hedging policies.
VFDS selects dynamic features for efficient HAR tasks, optimizing performance-cost trade-offs.
problem Optimizing feature selection for varying costs and dynamic contexts in machine learning tasks.
method Bayesian learning framework with variational dynamic selection policy.
result VFDS selects different features under changing contexts, saving sensory costs while maintaining HAR accuracy.
A deep reinforcement learning method for cost-sensitive portfolio selection.
problem Non-stationary price series and complex asset correlations make feature learning hard, and practical cost constraints are not considered.
method A two-stream portfolio policy network and a cost-sensitive reward function are developed using deep reinforcement learning.
result The method achieves superior performance in profitability, cost-sensitivity, and representation abilities.
Robust optimization and statistical robustness improve robot navigation policies.
problem Efficiently finding optimal robot navigation policies in uncertain environments.
method Combining robust optimization and statistical robustness with improved Bayesian optimization techniques.
result Safe and repeatable robot navigation policies are achieved with improved robust optimization methods.
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…
PS framework selects best policy from library for CSO problems.
problem Policy selection in CSO with heterogeneous performance across covariate space.
method PS framework constructs library of candidate policies and learns a meta-policy to select the best one.
result PS consistently outperforms best single policy in heterogeneous CSO problems.
BOMS enhances offline MBRL by improving model selection with Bayesian optimization.
problem Inaccurate model selection in offline MBRL due to distribution shift.
method Proposes BOMS, an active model selection framework using Bayesian optimization.
result Improves model selection with only a small amount of online interaction.
Enhances index selection for databases with task-specific inductive biases.
problem Challenges in traditional and automatic tuning strategies for database index set selection.
method Applies deep RL with task-specific inductive biases to index set selection, reformulating the problem as permutation learning.
result Improves index selection, achieving up to 40% smaller configurations with similar latency.
This work characterizes reward function partial identifiability and its impact on policy optimization.
problem Reward function partial identifiability in complex tasks.
method Formal characterisation of partial identifiability using various reward learning data sources.
result Unified framework for comparing data sources and downstream tasks by their invariances.
SEEK algorithm selects minimal state in reinforcement learning for better policy learning.
problem Challenges in obtaining a state representation that is parsimonious and satisfies the Markov property.
method SEEK algorithm estimates the minimal sufficient state in reinforcement learning.
result The SEEK algorithm achieves selection consistency in large samples.
ESPD improves learning efficiency in sparse reward reinforcement learning.
problem Sparse reward reinforcement learning challenges.
method Evolutionary Stochastic Policy Distillation (ESPD) based on drifted random walk insight.
result High learning efficiency demonstrated in MuJoCo robotics control suite experiments.
Algorithm selects optimal experiments in Markov chains to learn unknown quantities.
problem Designing efficient experiments in Markov chains to learn about unknown quantities.
method Proposes extsc{markov-design} algorithm for sequential policy selection.
result Algorithm provably converges to optimal measurement allocation.
This work improves policy evaluation and selection using logarithmic smoothing for pessimistic off-policy estimation.
problem Offline evaluation and selection of policies from past data.
method Develops novel concentration bounds and a logarithmically smoothed estimator (LS) for improved policy selection and learning.
result The logarithmically smoothed estimator (LS) provides tighter bounds and better policy selection and learning.
The study improves compound selection in in silico screening by focusing on model's ability to predict desirable outcomes.
problem Improving compound selection in in silico screening to reduce errors and enhance generalization.
method Extending learning theory, the study analyzes the impact of selection policies on generalization and proposes a method to mitigate challenges.
result Generalization can be enhanced by considering a model's ability to predict the fraction of desired outcomes in a batch.
Paper proposes an active multi-step TD algorithm for reinforcement learning.
problem Challenging decision making and control tasks in reinforcement learning.
method Active stepsize learning and adaptive multi-step TD algorithm with context-aware mechanism.
result Competitive results compared to other reinforcement learning baselines on discrete and continuous space tasks.
Speech recognition systems have achieved high recognition performance for several tasks. However, the performance of such systems is dependent on the tremendously costly development work of preparing vast amounts of task-matched transcribed speech data for supervised training. The key problem here is the cost of transc…
Framework improves policy generalizability under biased training data.
problem Learning policies that generalize to a target population from biased training data.
method Characterizes sample selection bias using a selection variable, optimizes minimax value over uncertainty set, derives efficient algorithm.
result Policies generalize to target population, outperform standard methods.
Paper tackles policy selection in offline RL without hyperparameters.
problem Selecting between policies and value functions in offline RL.
method Designs hyperparameter-free algorithms based on BVFT for policy selection.
result Demonstrates effectiveness in discrete-action benchmarks like Atari.
In the field of reinforcement learning there has been recent progress towards safety and high-confidence bounds on policy performance. However, to our knowledge, no practical methods exist for determining high-confidence policy performance bounds in the inverse reinforcement learning setting---where the true reward fun…
Transfer learning significantly accelerates the reinforcement learning process by exploiting relevant knowledge from previous experiences. The problem of optimally selecting source policies during the learning process is of great importance yet challenging. There has been little theoretical analysis of this problem. In…
The goal of task transfer in reinforcement learning is migrating the action policy of an agent to the target task from the source task. Given their successes on robotic action planning, current methods mostly rely on two requirements: exactly-relevant expert demonstrations or the explicitly-coded cost function on targe…
ReSkill reconciles RL skill creation with policy optimization.
problem RL policies lack reusable strategies across tasks.
method Integrates skill creation into RL loop with three mechanisms.
result Consistently outperforms existing methods, especially on unseen tasks.
A new method for evaluating and selecting policies in contextual bandits improves confidence intervals and policy quality.
problem Evaluating and selecting policies in contextual bandits with logged data.
method Self-normalized Importance Weighting (SN) estimator with Efron-Stein tail inequality and multiplicative bias control.
result The method provides tighter confidence intervals and better policy selection compared to competitors.
PBVFs generalize across policies using learned value functions.
problem RL algorithms forget information about old policies when updating value functions to track the learned policy.
method Introduce Parameter-Based Value Functions (PBVFs) that include policy parameters in their inputs, enabling them to generalize across different policies.
result PBVFs enable zero-shot learning of new policies that outperform any policy seen during training.
Simplifies RL training with fewer techniques, reducing bias and instability.
problem Training instabilities and high sample complexity in RL.
method Introduced a simple deterministic policy gradient, used propensity estimation, and delayed policy updates.
result Improved performance and reduced sample complexity through these techniques.
Paper tackles policy selection with logged data and limited online interactions.
problem Safe evaluation and deployment of offline reinforcement learning policies.
method Active offline policy selection combining logged data with online interaction.
result Improves upon state-of-the-art OPE estimates and pure online policy evaluation.
Agent learns causal relationships from visual data to perform tasks.
problem Performing tasks in novel environments with latent causal structures.
method Learning-based approach to induce causal graphs from visual observations, using attention mechanisms.
result Effective generalization to new tasks with unseen causal structures.
This paper uses deep reinforcement learning to optimize stock portfolios considering transaction costs and risks.
problem Optimizing stock portfolios with transaction costs and risks.
method Formulated stock portfolio optimization as a reinforcement learning problem, applied DDPG, GDPG, and PPO algorithms, and used Wavelet Transform.
result DDPG and GDPG algorithms outperformed PPO in continuous action space.