Model-Based Offline Planning (MBOP) learns models from offline data to control systems directly.
problem Training RL policies from offline data without direct system interaction.
method Generates models from offline data and uses planning to control the system.
result Near-optimal policies found for simulated systems with minimal real-time interaction.
New policy for non-stationary multi-armed bandits with recovering rewards.
problem Non-stationary multi-armed bandits with recovering rewards.
method Purely Periodic Policies integrating upper confidence bound procedure.
result Approximately O ~ ( N T ) \widetilde{\mathcal O}(N\sqrt{T}) O ( N T ) regret against the offline benchmark. Paper addresses offline policy evaluation in RL, achieving near-optimal bounds for various policy classes.
problem Evaluate all policies in a class simultaneously for offline RL.
method Uniform convergence in OPE for various policy classes, achieving optimal episode complexity.
result Achieves optimal episode complexity of O(H^3/d_mε^2) for identifying ε-optimal policies.
We propose a plan online and learn offline (POLO) framework for the setting where an agent, with an internal model, needs to continually act and learn in the world. Our work builds on the synergistic relationship between local model-based control, global value function learning, and exploration. We study how local traj…
MOReL learns offline RL policies using pessimistic MDPs.
problem Offline RL's data efficiency and velocity.
method Two-step process: learn P-MDP and near-optimal policy in it.
result MOReL is minimax optimal and matches state-of-the-art results.
Complex networks are often either too large for full exploration, partially accessible, or partially observed. Downstream learning tasks on these incomplete networks can produce low quality results. In addition, reducing the incompleteness of the network can be costly and nontrivial. As a result, network discovery algo…
MO2 learns useful behaviours from past experience for new tasks.
problem Discovering useful behaviours from past experience and transferring them to new tasks.
method Model-Based Offline Options (MO2) framework supporting sample-efficient bottleneck option discovery over continuous state-action spaces.
result MO2 outperforms recent option learning methods on complex long-horizon continuous control tasks.
Papers learn from data to make decisions without interacting, improving on previous methods.
problem Achieving optimal decision-making from offline data with non-linear function approximation.
method Pessimistic Nonlinear Least-Square Value Iteration (PNLSVI) with three innovative components.
result Achieves minimax optimal instance-dependent regret for non-linear function approximation.
Paper tackles robust offline RL for non-Markovian processes, improving efficiency and applicability.
problem Learning robust policies for non-Markovian decision processes with limited offline data.
method Proposes a novel algorithm with dataset distillation and LCB design for robust values, derived new dual forms, and introduces concentrability coefficients.
result Proves polynomial sample efficiency for finding ε-optimal robust policies.
New method optimizes experiments under constraints.
problem Adapting BED to dynamic constraints in real-world tasks.
method Offline pre-training of an amortized policy and posterior network with online multi-step lookahead planning.
result Significantly more informative design sequences than existing methods.
New RL method explores environments without rewards, achieving efficient policy generation.
problem Efficiently exploring unknown environments without predefined rewards.
method Optimistic value-iteration algorithm with kernel and neural function approximations.
result Achieves O ~ ( 1 / ε 2 ) \widetilde{\mathcal{O}}(1 /\varepsilon^2) O ( 1/ ε 2 ) sample complexity for generating policies or equilibria. Paper tackles offline preference-based RL with human feedback.
problem Offline Preference-based Reinforcement Learning with preference feedback.
method Two-step approach: MLE for reward estimation and distributionally robust planning.
result First guarantee for learning any target policy with polynomial samples.
Meta-agent learns effective exploration from offline data.
problem Design a meta-agent to quickly maximize reward in unseen tasks.
method Bayesian RL approach with adaptive neural belief estimate.
result Meta-agent learns effective exploration behavior from diverse tasks.
New approach handles stochastic and partially-observable environments using discrete autoencoders and Monte Carlo tree search.
problem Challenges in planning for stochastic and partially-observable environments.
method Uses discrete autoencoders and a stochastic variant of Monte Carlo tree search.
result Significantly outperforms MuZero on stochastic chess and scales to DeepMind Lab.
New algorithm learns optimal policies in strategic MDPs with private types.
problem Optimal policy learning in strategic MDPs with private types and information asymmetry.
method PLAN algorithm using instrumental variable regression and pessimism principle.
result PLAN achieves near-optimal policy with 1 / K 1 / \sqrt{K} 1/ K optimality. The paper proposes autoregressive models for better offline RL.
problem Offline RL policy evaluation and optimization challenges.
method Autoregressive dynamics models for sequential state and reward prediction.
result Autoregressive models outperform standard methods in log-likelihood and RL tasks.
EDGI improves sample efficiency and generalization in tasks with spatial and temporal symmetries.
problem Sample inefficiency and poor generalization in tasks with geometric symmetries.
method Equivariant Diffuser framework, SE(3)xZxSn-equivariant diffusion model.
result EDGI is more sample efficient and generalizes better than non-equivariant models.
Bayesian optimization usually assumes that a Bayesian prior is given. However, the strong theoretical guarantees in Bayesian optimization are often regrettably compromised in practice because of unknown parameters in the prior. In this paper, we adopt a variant of empirical Bayes and show that, by estimating the Gaussi…
This paper offers a methodological contribution at the intersection of machine learning and operations research. Namely, we propose a methodology to quickly predict tactical solutions to a given operational problem. In this context, the tactical solution is less detailed than the operational one but it has to be comput…
Improves BC policies by generating new plausible trajectories.
problem Sub-optimal data quality in BC leads to poor policy performance.
method Trajectory Stitching (TS) generates new plausible transitions.
result TS significantly improves behavioural policies over original data.
Improves RL from historical data by stitching trajectories.
problem Lack of high-quality data for offline RL.
method Trajectory Stitching (TS) to augment historical data with synthetic actions.
result Improves RL policy performance over baseline.
This work learns visual representations for deformable objects using contrastive estimation.
problem Challenges in learning plannable visual representations for deformable objects.
method Jointly optimizes visual representation and dynamics models using contrastive estimation.
result Substantial improvements in performance over standard model-based learning techniques.
FTPL method shows near-optimal regret bounds for AMDPs with bandit feedback.
problem Minimizing regret in AMDPs with adversarial losses and bandit feedback.
method Follow-the-Perturbed-Leader (FTPL) method for AMDPs.
result FTPL achieves near-optimal regret bounds for AMDPs with bandit feedback.
Latent variable models improve RL by facilitating efficient learning and exploration.
problem Improving sample efficiency in reinforcement learning.
method Representation view of latent variable models for state-action value functions, incorporating kernel embeddings and UCB exploration.
result Established sample complexity of the proposed approach in online and offline settings, demonstrated superior performance in benchmarks.
AdaCat improves density estimation and planning in autoregressive models.
problem Efficiently modeling sharp density changes in continuous data.
method Adaptive Categorical Discretization (AdaCat) for autoregressive models.
result Improves density estimation and planning in various data types.
Models for predicting aircraft motion are an important component of modern aeronautical systems. These models help aircraft plan collision avoidance maneuvers and help conduct offline performance and safety analyses. In this article, we develop a method for learning a probabilistic generative model of aircraft motion i…
A new algorithm learns optimal personalized treatment plans online with low regret.
problem Learning optimal dynamic treatment regimes in an online setting.
method Developed a novel algorithm balancing exploration and exploitation for rate-optimal regret.
result Guaranteed rate-optimal regret for linear transition and reward models.
This paper offers a methodological contribution at the intersection of machine learning and operations research. Namely, we propose a methodology to quickly predict expected tactical descriptions of operational solutions (TDOSs). The problem we address occurs in the context of two-stage stochastic programming where the…
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.
Paper tackles robust decision-making from multiple sites with shared structure.
problem Learning robust sequential decisions from heterogeneous multi-site datasets.
method Group-Robust MDPs with d-rectangular uncertainty sets, feature-wise worst-case aggregation, and cluster-level pooling.
result Proves suboptimality bound for robust planning policy under robust partial coverage assumption.
A new algorithm reduces memory usage for deep learning models.
problem Training deep learning models requires significant memory.
method Dynamic Tensor Rematerialization (DTR) is a greedy online algorithm that dynamically plans recomputations.
result DTR achieves comparable performance to optimal static checkpointing with only a small memory budget.
Paper tackles offline meta-reinforcement learning with a new algorithm.
problem Performing reinforcement learning on limited data from a new task.
method Meta-Actor Critic with Advantage Weighting (MACAW) algorithm.
result Achieves notable gains over prior methods on offline meta-RL benchmarks.
The paper reclassifies RL algorithms using inference concepts.
problem To provide a unified perspective on RL algorithms.
method Using the control as inference framework, the paper classifies RL algorithms as amortised and iterative inference.
result A wide range of RL algorithms can be classified in this new manner.
Algorithm balances online and offline data for linear bandits.
problem Online learning with an offline dataset in linear bandits.
method Proposes a linear bandit algorithm that uses offline data early and increasingly favors exploration as the horizon grows.
result Establishes regret bounds showing competitive performance with both purely online and offline solutions.
Algorithm learns from offline data to improve performance in target environment.
problem Learning from offline data in a target environment with unknown shifts.
method Adaptive algorithm that uses offline data to improve performance when informative.
result Algorithm provably improves performance over purely online learning when offline data are informative.
WebGUM learns web navigation from multimodal data, outperforming previous methods.
problem Limited generalization from domain-specific models in web navigation.
method Instruction-following multimodal agent trained on vision-language foundation models.
result Significant improvement in web navigation performance on benchmarks.
Algorithm reduces online regret by leveraging offline data in linear bandits.
problem Online regret minimization in linear bandits with offline data.
method OOPE algorithm using extended D-optimal design.
result Substantial reduction in online regret compared to prior work.
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.
Bridges uplift modeling and sequential decision-making with online budget allocation.
problem Treatment allocation under budget constraints in digital advertising.
method Budget-Constrained Causal Bandits (BCCB) integrates learning, exploration, and budget pacing.
result Data-efficiency crossover: BCCB operates effectively from the first user, 3-5x lower performance variance.
New method tackles safe reinforcement learning from offline data.
problem Learn optimal policies from fixed data while adhering to safety constraints.
method Combines offline RL with online optimization to minimize cumulative cost.
result Proves approximate optimality of the approach under certain conditions.
Understanding and interacting with everyday physical scenes requires rich knowledge about the structure of the world, represented either implicitly in a value or policy function, or explicitly in a transition model. Here we introduce a new class of learnable models--based on graph networks--which implement an inductive…
Improves diffusion model performance and efficiency through classical search.
problem Tackles inference-time control in diffusion models.
method Proposes a framework combining local and global search for efficient navigation.
result Significant gains in performance and efficiency across various domains.
Fine-tuning RL with offline data reduces online interactions.
problem Optimizing RL with limited online interactions and offline data.
method Developed algorithm extsc{FTPedel} for MDPs with linear structure.
result Optimally reduces the number of online interactions needed.
Paper offers a fast convergence theory for offline decision making.
problem Offline decision making problems, including reinforcement learning and off-policy evaluation.
method Introduces a framework (DMOF) and algorithm (EDD) with a fast convergence guarantee.
result Demonstrates a fast convergence guarantee with a lower bound complement.
Study finds methods to learn multiple solutions from single task in offline RL.
problem Learning multiple solutions from a single task in offline RL.
method Proposed algorithms for offline RL.
result Empirical results show learning of multiple solutions in offline RL.
This work bridges offline RL and DRL to address distributional shift.
problem Distributional shift in offline RL due to difference in state-action visitation distributions.
method Proposes offline RL algorithms using DRL framework, characterizes sample complexity under single policy concentrability.
result Demonstrates superior performance of proposed algorithms through simulations.
FOCUS improves offline RL by incorporating causal structure into world-models.
problem Learning effective policies from historical data without interaction.
method FOCUS proposes a practical algorithm that learns and leverages causal structure in offline RL.
result FOCUS outperforms plain model-based offline RL algorithms and other causal model-based RL algorithms.
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.