A new approach for cooperative multi-agent reinforcement learning with limited communication, reducing the number of communication rounds.
problem Limited communication in decentralized MARL systems leads to outdated information and unstable learning.
method Base policy prediction technique to estimate gradients and collect samples for a sequence of base policies.
result The proposed algorithm converges to an ε-Nash equilibrium with significantly fewer communication rounds and samples.
We introduce Recurrent Predictive State Policy (RPSP) networks, a recurrent architecture that brings insights from predictive state representations to reinforcement learning in partially observable environments. Predictive state policy networks consist of a recursive filter, which keeps track of a belief about the stat…
This study models FOMC policy decisions using debate-based LLMs.
problem Accurately predicting central bank policy decisions, especially FOMC's, is challenging.
method A novel framework that simulates FOMC's collective decision-making process through iterative rounds of LLMs interacting as agents.
result The debate-based approach significantly outperforms standard LLMs in prediction accuracy.
Optimizes deep reinforcement learning for energy-efficient video streaming.
problem Minimizing energy consumption in video streaming over mobile networks.
method Integrates DDPG algorithm with partially known model to reduce signaling overhead and improve convergence speed.
result Proposed policy converges to optimal policy with improved convergence speed.
The paper improves off-policy evaluation in contextual bandits using conformal prediction.
problem Quantifying the performance of a target policy using data from a different behavior policy.
method Proposes a novel algorithm based on a PAC-valid conformal prediction framework to construct probably approximately correct prediction intervals.
result Establishes PAC-type bounds on coverage, improving theoretical guarantees.
This paper proposes a novel deep reinforcement learning architecture that was inspired by previous tree structured architectures which were only useable in discrete action spaces. Policy Prediction Network offers a way to improve sample complexity and performance on continuous control problems in exchange for extra com…
This study improves stock price prediction by incorporating anticipated macroeconomic policy changes.
problem Improving accuracy in stock price prediction.
method Incorporates future expected macroeconomic policy changes and historical stock prices.
result Our method outperforms conventional approaches with an RMSE of 1.61 compared to 1.75.
Extends OPE to evaluate policies using diverse logging data.
problem Evaluate policies using log data from different policies.
method Develops an OPE method for various logging policies.
result Method's predictions converge to true performance as sample size increases.
Accelerates policy optimization in RL with optimistic and adaptive updates.
problem Improving policy optimization methods in reinforcement learning.
method Integrates foresight into policy improvement step via optimistic and adaptive updates.
result Designs an optimistic policy gradient algorithm, adaptive via meta-gradient learning.
Adaptive vehicle trajectory prediction for safer autonomous driving.
problem Inability of current methods to guarantee physical feasibility and adapt to human driving policies.
method Bayesian recurrent neural network combining policy and physical models, with gradient-based training and parameter adaptation.
result The proposed method ensures physical feasibility and adaptability to human driving policies.
Agents compose pre-trained policies for complex tasks, improving zero-shot performance.
problem Challenges in long-horizon predictions and estimating visitation distributions induced by policy sequences.
method Learn predictive jumpy world models of multi-step dynamics, enhancing predictions with a consistency objective.
result Compositional planning with jumpy world models yields, on average, a 200% relative improvement over primitive actions on long-horizon tasks.
Optimizes state monitoring in Markovian systems with cost constraints.
problem Balancing state queries with prediction costs in Markovian systems.
method Greedy policy and SGD-based learning variant for optimal predict-query tradeoff.
result Greedy policy is suboptimal but performs close to optimal under certain conditions.
Imagine a patient in critical condition. What and when should be measured to forecast detrimental events, especially under the budget constraints? We answer this question by deep reinforcement learning (RL) that jointly minimizes the measurement cost and maximizes predictive gain, by scheduling strategically-timed meas…
Optimizes trading policies using future price forecasts.
problem Static reinforcement learning agents lack mechanisms for using price forecasts at inference time.
method FPILOT framework inspired by Model Predictive Control (MPC). Uses a predictive model to construct an allocation-based imagined return objective at each decision step.
result Consistent improvements in total return and risk-adjusted metrics across various policy learning algorithms.
A deep learning model predicts future cache accesses with high accuracy.
problem Improving cache management and performance through better prediction of future data accesses.
method Proposed a LSTM-based recurrent neural network model to predict future cache accesses using only a cache trace as input.
result The proposed model achieves high prediction accuracy and outperforms state-of-the-art practical policies.
Unified framework for reliable uncertainty quantification in RL.
problem Uncertainty quantification in high-stakes reinforcement learning.
method Unified conformal prediction framework integrating distributional RL and conformal calibration.
result Significantly improved coverage and reliability over standard methods.
New method optimizes treatment policies to avoid winner's curse.
problem Winner's curse in treatment policy optimization.
method Inference-aware policy optimization.
result Optimizes for both estimated performance and downstream evaluation.
MA-COPP predicts multi-agent system outcomes using data from a different policy, with probabilistic guarantees.
problem Predicting outcomes in multi-agent systems using data from a different policy.
method Conformal prediction framework applied to multi-agent systems, avoiding exhaustive search.
result Achieves probabilistic guarantees for multi-agent system predictions.
Sample efficiency is critical in solving real-world reinforcement learning problems, where agent-environment interactions can be costly. Imitation learning from expert advice has proved to be an effective strategy for reducing the number of interactions required to train a policy. Online imitation learning, which inter…
This paper proposes a method for estimating the effect of a policy intervention on an outcome over time. We train recurrent neural networks (RNNs) on the history of control unit outcomes to learn a useful representation for predicting future outcomes. The learned representation of control units is then applied to the t…
New approach reduces simulator exploitation by improving strategic robustness.
problem Simulator exploitation leading to reality gap between simulation and real-world performance.
method Formulated as a zero-sum minimax game, providing theoretical guarantees and a convergent active data selection algorithm.
result Proves convergence and reduces prediction error in strategically important regions by 1.5-2.2 times.
New approach reduces simulator exploitation by learning robust models.
problem Simulator exploitation leading to reality gap in reinforcement learning.
method Formulated as a zero-sum minimax game between model player and policy player, providing theoretical guarantees and a convergent active data selection algorithm.
result Reduces prediction error in strategically important regions by 1.5-2.2 times and enables near-optimal real-world performance.
Improves data efficiency in multi-agent control tasks using model-based reinforcement learning.
problem Limited data efficiency in reinforcement learning for multi-agent tasks.
method Decentralized model-based policy optimization (DMPO) framework.
result DMPO achieves superior data efficiency and matches model-free methods using true models.
New methods improve robust decision-making under uncertainty in off-policy evaluation.
problem Statistical uncertainty and causal considerations in off-policy evaluation.
method Marginal Ratio (MR) estimator, Conformal Off-Policy Prediction (COPP), causal bounds.
result Improved robustness and uncertainty quantification in off-policy decision-making.
We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects. In contrast to most existing model-based reinforcement learning and planning methods, which prescribe how a model should be used to arrive at a policy, I2As learn to inter…
Optimal policies identified for learning systems with a malicious expert.
problem Adversarial attacks on learning systems combining expert advice.
method Analysis of offline and online settings, dynamic programming for online setting.
result Greedy policy is asymptotically optimal with approximation ratio for offline setting.
MAGE optimizes policies using action gradients from model-based learning.
problem Lack of direct gradient information from critics in actor-critic methods.
method Model-based actor-critic algorithm that learns action-value gradient.
result MAGE outperforms model-free and model-based baselines on continuous control tasks.
Overparameterized models generalize well in offline contextual bandits, but policy-based algorithms struggle.
problem The performance gap between value-based and policy-based algorithms in offline contextual bandits with overparameterized models.
method Analysis of action-stability in objectives and formal proofs of regret bounds.
result The performance gap is due to action-stability of objectives, with value-based objectives being stable and policy-based objectives unstable.
We study how the behavior of deep policy gradient algorithms reflects the conceptual framework motivating their development. To this end, we propose a fine-grained analysis of state-of-the-art methods based on key elements of this framework: gradient estimation, value prediction, and optimization landscapes. Our result…
Model-based reinforcement learning has the potential to be more sample efficient than model-free approaches. However, existing model-based methods are vulnerable to model bias, which leads to poor generalization and asymptotic performance compared to model-free counterparts. In addition, they are typically based on the…
Gradient-based algorithm improves model performance with triage.
problem Improving model accuracy with human expert involvement.
method Formal characterization of triage, optimal triage policy as deterministic threshold rule, gradient-based algorithm.
result Gradient-based algorithm finds triage policies and models with increasing performance.
COPP provides reliable intervals for outcomes under a new policy in contextual bandits.
problem Lack of reliable predictive intervals for outcomes under a new policy in contextual bandits.
method Conformal prediction applied to contextual bandits.
result COPP provides finite-sample guarantees without additional assumptions.
Model-based reinforcement learning (MBRL) with model-predictive control or online planning has shown great potential for locomotion control tasks in terms of both sample efficiency and asymptotic performance. Despite their initial successes, the existing planning methods search from candidate sequences randomly generat…
Learning policies on data synthesized by models can in principle quench the thirst of reinforcement learning algorithms for large amounts of real experience, which is often costly to acquire. However, simulating plausible experience de novo is a hard problem for many complex environments, often resulting in biases for …
Study evaluates new models using human feedback from another model.
problem Evaluate a new model using human feedback collected for another model.
method Formalize problem, propose model-based and model-free estimators, analyze unbiasedness, and empirically evaluate.
result Proposed estimators can predict absolute values, rank, and optimize evaluated policies.
Develops methods to estimate and quantify uncertainty in off-policy evaluation.
problem Uncertainty quantification in off-policy evaluation for new policy deployment.
method Designs a pseudo policy to generate subsamples and applies conformal prediction.
result Valid interval estimators for target policy's return with uncertainty quantification.
Model-free approaches for reinforcement learning (RL) and continuous control find policies based only on past states and rewards, without fitting a model of the system dynamics. They are appealing as they are general purpose and easy to implement; however, they also come with fewer theoretical guarantees than model-bas…
Current clinical practice to monitor patients' health follows either regular or heuristic-based lab test (e.g. blood test) scheduling. Such practice not only gives rise to redundant measurements accruing cost, but may even lead to unnecessary patient discomfort. From the computational perspective, heuristic-based test …
We present a predictor-corrector framework, called PicCoLO, that can transform a first-order model-free reinforcement or imitation learning algorithm into a new hybrid method that leverages predictive models to accelerate policy learning. The new "PicCoLOed" algorithm optimizes a policy by recursively repeating two ste…
New RL method learns value function for many policies using few key states.
problem Evaluate and improve policies in continuous control problems.
method Combines actor-critic architecture and policy embedding to learn a single value function for many policies.
result Value function minimizes prediction error by learning a small set of 'probing states' and their impact on policies' returns.
The task of multi-step ahead prediction in language models is challenging considering the discrepancy between training and testing. At test time, a language model is required to make predictions given past predictions as input, instead of the past targets that are provided during training. This difference, known as exp…
Proposes a convergent TD algorithm for off-policy RL.
problem Learning value function from different policies in RL.
method Convergent on-policy TD algorithm with linear function approximation.
result Proposes a convergent TD algorithm for off-policy RL.
Self-consistent models improve reinforcement learning by aligning predictions with future values.
problem Improving reinforcement learning by aligning model predictions with future values.
method Proposes multiple self-consistency updates to encourage a learned model and value function to be consistent with each other.
result Self-consistency helps both policy evaluation and control in both tabular and function approximation settings.
We introduce the value iteration network (VIN): a fully differentiable neural network with a `planning module' embedded within. VINs can learn to plan, and are suitable for predicting outcomes that involve planning-based reasoning, such as policies for reinforcement learning. Key to our approach is a novel differentiab…
Paper proposes BMPO to optimize policies using bidirectional models.
problem Model-based reinforcement learning's reliance on forward model accuracy.
method Develops BMPO using both forward and backward models for policy optimization.
result BMPO outperforms state-of-the-art methods in sample efficiency and asymptotic performance.
New algorithms improve policy evaluation in reinforcement learning.
problem Off-policy stability and on-policy efficiency issues in policy evaluation.
method Introduced novel algorithms using oblique projection method.
result Demonstrated both off-policy stability and on-policy efficiency.
Model-based reinforcement learning approaches carry the promise of being data efficient. However, due to challenges in learning dynamics models that sufficiently match the real-world dynamics, they struggle to achieve the same asymptotic performance as model-free methods. We propose Model-Based Meta-Policy-Optimization…
AACE learns treatment policies from EHRs using annotations to improve accuracy.
problem Learning treatment policies from multimodal EHRs with bias and inefficiency.
method Annotation-assisted coarsened effects (AACE) method.
result AACE outperforms existing methods in predicting treatment benefit from multimodal EHRs.