Aims to optimize goal sampling in deep reinforcement learning.
problem The sampling of goals affects deep reinforcement learning performance.
method Curriculum goal masking method to focus on medium difficulty goals.
result Focusing on medium difficulty goals leads to better learning performance.
HGG generates goals to improve sample efficiency in robotic tasks.
problem Efficiency in reinforcement learning with sparse reward signals.
method Generates valuable hindsight goals for reinforcement learning.
result Significantly improved sample efficiency over HER.
A method for setting up an automatic curriculum for reinforcement learning tasks.
problem Improving sample efficiency in multi-task reinforcement learning.
method Propose a goal proposal module that prioritizes goals maximizing epistemic uncertainty of the Q-function.
result Significant performance gains over current methods in 13 multi-goal robotic tasks and 5 navigation tasks.
Max entropy exploration guides reinforcement learning agents to pursue achievable goals.
problem Achieving distant test-time goals in long-horizon tasks.
method Optimize entropy of historical achieved goals by focusing on sparsely explored areas.
result Order of magnitude better sample efficiency on long-horizon multi-goal tasks.
A novel framework uses goal-conditioned reinforcement learning to generate diverse samples.
problem Generating high-quality, diverse samples from generative models.
method Two agents: GC-agent learns to reconstruct the training set, S-agent learns to imitate GC-agent without knowing the goals.
result Empirically, the method generates diverse and high-quality samples in image synthesis.
Unified algorithm tackles various RL goals like reward-free and preference-based learning.
problem Unified approach to multiple RL learning goals.
method Decision-Estimation Coefficient (DEC) framework.
result Unified algorithm handles various learning goals with a single framework.
The paper improves HER by prioritizing virtual goals and removing misleading samples.
problem Sparse reward functions in reinforcement learning.
method Prioritizing virtual goals based on instructiveness and removing misleading samples.
result Significant improvement in success rate and sample efficiency.
A novel RL objective and prioritization framework improve performance and sample-efficiency in multi-goal tasks.
problem Learning diverse goals in multi-goal reinforcement learning.
method Maximum entropy regularization for objective and prioritization framework.
result Promising improvements in performance and sample-efficiency on multi-goal robotic tasks.
Intrinsically motivated goal exploration processes enable agents to autonomously sample goals to explore efficiently complex environments with high-dimensional continuous actions. They have been applied successfully to real world robots to discover repertoires of policies producing a wide diversity of effects. Often th…
The paper proposes a method for a robot to learn skills from imagined goals.
problem Training robots to perform a wide range of tasks with raw sensory input.
method Combining unsupervised representation learning and reinforcement learning of goal-conditioned policies.
result The method learns skills that can operate on raw image observations and outperforms prior techniques.
Adapts Floyd-Warshall algorithm for RL to improve multi-goal task learning.
problem Limited transfer of learned information in model-free RL for dynamic goal tasks.
method Adapts Floyd-Warshall algorithm for RL to learn goal-conditioned action-value functions.
result FWRL achieves higher reward strategies in multi-goal tasks with fewer samples.
Method maps state space using landmarks for universal goal reaching.
problem Learning the Universal Value Function Approximator (UVFA) for long-range goals is challenging.
method Hierarchical modeling with a dynamic landmark-based map and a value network.
result The method enables agents to reach long-range goals at the early training stage.
This work improves imitation learning and goal-conditioned RL by estimating value densities.
problem Effective solutions for imitation and goal-conditioned reinforcement learning require reliably reaching specified states or demonstrations.
method The approach uses recent advances in density estimation to learn value functions efficiently and without hindsight bias.
result The method achieves state-of-the-art demonstration sample-efficiency in imitation learning and is both efficient and bias-free in goal-conditioned reinforcement learning.
C-Learning estimates reachability over time to solve multi-goal tasks.
problem Multi-goal reaching challenges in reinforcement learning.
method Cumulative accessibility functions and recurrence relations.
result Optimal cumulative accessibility functions are monotonic in horizon.
This paper examines how different decoding algorithms for LLMs align with various goals.
problem Consistency of decoding algorithms with different goals in LLMs.
method Analysis of greedy, lookahead, random sampling, and temperature-scaled random sampling algorithms.
result Random sampling is consistent with the true probability distribution, but other goals require optimal algorithms for specific probability distributions.
New method improves robot learning from vision with better sample efficiency.
problem Scaling reinforcement learning to real robots from vision.
method State representation learning to extract relevant features.
result Improved sample efficiency and robustness to hyper-parameters.
GOALS improves learning rate selection for dynamic MBSS in deep learning.
problem Challenges in selecting learning rates for dynamic MBSS in deep learning.
method Gradient-only approximation line search (GOALS) for dynamic MBSS loss functions.
result GOALS reduces model errors in multimodal cases.
Framework discovers sub-goals for better exploration in RL tasks.
problem Improving exploration in sequential decision making under partial observability.
method Variational intrinsic control framework with information theoretic regularizer.
result Sub-goals discovered without explicit supervision lead to better exploration and sample efficiency.
PlanGAN uses GANs to plan efficient trajectories for multi-goal tasks in sparse reward environments.
problem Learning with sparse rewards in multi-goal environments.
method PlanGAN combines GANs to generate trajectories leading to specified goals, then combines these into a planning algorithm.
result PlanGAN achieves comparable performance to model-free RL but is 4-8 times more sample efficient.
Unified perspective unites Bayesian optimization and active learning for efficient goal-oriented optimization.
problem Efficiently optimize expensive engineering and scientific problems with limited data.
method Unified framework linking Bayesian infill criteria and active learning criteria.
result Unified approach formalizes Bayesian infill criteria and active learning criteria.
We design a new myopic strategy for a wide class of sequential design of experiment (DOE) problems, where the goal is to collect data in order to to fulfil a certain problem specific goal. Our approach, Myopic Posterior Sampling (MPS), is inspired by the classical posterior (Thompson) sampling algorithm for multi-armed…
OptiGAN uses GAN and RL to optimize sequence generation for specific goals.
problem Challenging in sequence generation tasks to generate sequences with specific desired goals.
method Integrates GAN and RL to optimize desired goal scores using policy gradients.
result Achieves higher desired scores in text and real-valued sequence generation.
Improves reinforcement learning for complex tasks with sparse feedback.
problem Learning optimal policies from sparse feedback is challenging.
method Three algorithms based on Hindsight Experience Replay (HER) to improve performances.
result Vast improvement in final success rate and sample efficiency.
Eikonal-Constrained QRL improves goal-reaching in reinforcement learning.
problem Reward design and out-of-distribution generalization in reinforcement learning.
method Eikonal-Constrained Quasimetric Reinforcement Learning (Eik-QRL) using the Eikonal PDE.
result Eik-QRL achieves state-of-the-art performance in offline goal-conditioned navigation and manipulation tasks.
Framework improves agent's ability to learn from noisy images.
problem Agents tend to focus on distracting regions in unsupervised image-based goal exploration.
method Proposes a novel framework combining absolute Learning Progress with unsupervised image-based goal exploration.
result Agents successfully identify and ignore distracting regions, improving overall performance.
New method learns optimal environment and goal difficulty for reinforcement learning.
problem Lack of robust transfer in reinforcement learning.
method Self-Supervised Active Domain Randomization (SS-ADR).
result Optimal domain randomization strategy improves transfer in goal-directed tasks.
The study optimizes sampling in complex systems with probabilistic response distributions.
problem Calibrating and optimizing complex systems with probabilistic response distributions.
method Non-parametric Bayesian approach to modeling spatial fields of probability distributions, introducing adaptive sampling strategies.
result Adaptive sampling strategies improve system evaluations by guiding focus towards key features.
CDP improves RL performance and sample-efficiency by prioritizing rare goal states.
problem Learning from imbalanced data in RL.
method Curiosity-Driven Prioritization (CDP) framework.
result CDP improves both performance and sample-efficiency of RL agents.
Improves sparse reinforcement learning efficiency with OYMB.
problem Sparse rewards hinder reinforcement learning performance.
method Introduces OYMB, a sampler for HER to control minibatch makeup.
result HER combined with OYMB leads to faster real goal completion.
This paper proposes a method to learn from expert trajectories by decomposing tasks into sub-goals.
problem Learning complex goal-oriented tasks with sparse rewards and limited samples.
method The approach uses expert trajectories to decompose tasks into sub-goals, learning an extrinsic reward function and modulating sub-goal predictions.
result The method alleviates errors in imitation learning and solves complex tasks that other methods cannot.
Efficiently tests discrete distributions with limited memory and communication.
problem Testing discrete distributions with constraints on memory and communication.
method Developed efficient algorithms for uniformity/identity and closeness testing in streaming and distributed models.
result Nearly-tight lower bounds on sample complexity and communication cost for uniformity testing.
GOIMDA selects inputs to maximize expected influence on a goal functional, reducing data acquisition needs.
problem Challenges in active data acquisition for learning and optimization tasks in deep neural networks.
method GOIMDA uses inverse curvature and goal gradient to select inputs maximizing expected influence on a specified goal functional.
result GOIMDA achieves target performance with fewer labeled samples or function evaluations compared to baselines.
This paper studies active learning in the context of robust statistics. Specifically, we propose a variant of the Best Arm Identification problem for \emph{contaminated bandits}, where each arm pull has probability ε of generating a sample from an arbitrary contamination distribution instead of the true und…
Sample-Rank simplifies MO recommendations by sampling and ranking, improving revenue with stable conversion rates.
problem Multi-objective recommendations in online food ordering systems.
method Multi-goal sampling followed by ranking, reducing MO problem to LTR model.
result Significant lift in revenue (2.64%) with stable conversion rates, no drop in last-mile traversal.
PCHID improves sample efficiency in reinforcement learning tasks.
problem Sparse rewards make learning policies difficult in reinforcement learning.
method Hindsight Inverse Dynamics with Hindsight Experience Replay and Policy Continuation.
result PCHID significantly improves sample efficiency and final performance on multi-goal tasks.
Pre-trained language model boosts RL efficiency.
problem Low sample efficiency in RL, especially in lifelong learning.
method Use a pre-trained task-independent language model for transfer learning.
result Goal-conditional RL agents become more sample efficient.
The paper optimizes training samples for image denoising across different noise levels.
problem Training a denoiser for all noise levels with uniform sample distribution.
method Derives a dual ascent algorithm for optimal sampling distribution.
result The algorithm converges to an optimal sampling distribution for deep neural networks.
ADRL improves participant selection in MCS systems.
problem Designing a participant selection algorithm for different MCS systems with multiple goals.
method Auxiliary-task based deep reinforcement learning (ADRL) using transformers and pointer networks.
result ADRL outperforms other baselines in various MCS settings.
The paper tackles imbalance in production data by proposing sampling methods to improve model performance on underrepresented observations.
problem Imbalance in production data negatively impacts model predictive performance on underrepresented observations.
method Three sampling approaches are investigated to adjust for imbalance in training data and improve model performance.
result Fitting a model using sampled data yields a small reduction in overall predictive performance but a better performance on underrepresented observations.
AI bias arises from human-defined goals, not algorithmic flaws.
problem AI bias due to human-defined goals in LLMs.
method Purpose-conditioned cognition and revealing downstream use of LLM outputs.
result AI bias can be reduced by purpose-aware prompting but not fully by regularization.
Hybrid approach improves reinforcement learning efficiency.
problem Improving sample efficiency in reinforcement learning.
method Approximate model from Model-Free RL, use Mean First Passage Times for reachability, design new algorithms.
result Hybrid approaches converge with fewer iterations and samples.
The UN Sustainable Development Goals allude to the importance of infrastructure quality in three of its seventeen goals. However, monitoring infrastructure quality in developing regions remains prohibitively expensive and impedes efforts to measure progress toward these goals. To this end, we investigate the use of wid…
A new method for experimental design focuses on predicting downstream quantities of interest.
problem Designs that maximize parameter learning may not maximize downstream quantity prediction.
method Likelihood-free goal-oriented optimal experimental design (LF-GO-OED) using ABC density ratio estimation.
result LF-GO-OED maximizes the expected information gain for downstream quantities.
SNPL learns safe policies for multi-objective interventions with high confidence.
problem Designing effective digital interventions balancing multiple objectives with noisy data.
method Leverages algorithmic stability to learn policies with high-confidence guarantees.
result Offers dramatic improvements in safety and policy gains with smaller sample sizes.
Introduces HMC method for sampling Gibbs densities.
problem Sampling from Gibbs densities efficiently.
method Hamiltonian Monte Carlo (HMC) method based on Hamiltonian dynamics.
result Idealized HMC preserves the target distribution and converges under certain conditions.
The goal of two-sample tests is to assess whether two samples, SP∼Pn and SQ∼Qm, are drawn from the same distribution. Perhaps intriguingly, one relatively unexplored method to build two-sample tests is the use of binary classifiers. In particular, construct a dataset by pairing the n examples in $S_…
In supervised learning one wishes to identify a pattern present in a joint distribution P, of instances, label pairs, by providing a function f from instances to labels that has low risk EPℓ(y,f(x)). To do so, the learner is given access to n iid samples drawn from P. In many real world problem…
Directed exploration improves reinforcement learning efficiency and robustness.
problem Achieving good sample efficiency in reinforcement learning with efficient exploration.
method Directed exploration through goal-conditioned policies that are independent of uncertainty.
result Directed exploration is more efficient and robust to uncertainty than reward bonuses.