Introduces GAMPS for better model-based policy learning.
problem Misspecified model classes lead to poor policy estimates.
method Exploits current policy to learn approximate transition model, focusing on relevant parts of the environment.
result Empirically validated GAMPS on benchmark domains, demonstrating improved properties.
A new algorithm solves sparse reward tasks efficiently in robotics.
problem Sparse or misleading rewards in reinforcement learning.
method Multi-objective model-based policy optimization with three objectives.
result Multi-DEX solves sparse reward scenarios in fewer episodes than existing methods.
CF-GPS learns policies from logged data by considering counterfactual outcomes.
problem Learning policies from limited real experience in complex environments.
method Assumes logged real experience and models counterfactual outcomes. Uses structural causal models for evaluation.
result Improves policy evaluation and search results on a grid-world task.
Unified framework for policy improvement in RL with benefits in data efficiency and computation.
problem Improving data efficiency and computation in reinforcement learning for continuous control.
method Local, regularized policy improvement with tree search for continuous action spaces.
result Improves data efficiency and reduces wall-clock time in high-dimensional domains.
The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model and its uncertainties. Among the few proposed approaches, the recent…
PIPPS solves deep learning's exploding gradient problem by reparameterization gradients.
problem Exploding gradients in deep learning and model-based RL.
method Develops PIPPS framework, a flexible policy search method robust to chaos-like gradients.
result PIPPS improves over reparameterization gradients by up to 10^6 times.
Survey on algorithms for quick robot learning.
problem Efficiently learn robot controllers with limited data.
method Leverage prior knowledge and data-driven models.
result Combining prior knowledge and surrogate models improves learning.
PID control architectures are widely used in industrial applications. Despite their low number of open parameters, tuning multiple, coupled PID controllers can become tedious in practice. In this paper, we extend PILCO, a model-based policy search framework, to automatically tune multivariate PID controllers purely bas…
The paper proposes an iterative approach to batch reinforcement learning for safer and more informative data collection.
problem Learning policies that are too rigid and do not adapt to new data.
method Safe diversified model-based policy search in an iterative batch reinforcement learning framework.
result Improved learned policies through continuous data collection and adaptation.
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…
Proposes H-UCRL for efficient model-based RL with sublinear regret.
problem Greedy policy exploration in model-based RL ignores epistemic uncertainty.
method Reparameterizes plausible models, hallucinates control, augments input space, solves with greedy planners.
result H-UCRL achieves provably sublinear regret for Gaussian Process models.
The goal of reinforcement learning (RL) is to let an agent learn an optimal control policy in an unknown environment so that future expected rewards are maximized. The model-free RL approach directly learns the policy based on data samples. Although using many samples tends to improve the accuracy of policy learning, c…
Dual Policy Iteration combines fast and slow policies for better reinforcement learning performance.
problem Improving reinforcement learning algorithms for practical applications.
method Alternates between a fast, reactive policy and a slow, non-reactive policy, optimizing both under each other's supervision.
result Demonstrates improved performance on various continuous control Markov Decision Processes.
POPLIN improves model-based planning in complex environments.
problem Efficient planning in complex high-dimensional environments.
method Combines policy networks with online planning, optimizing parameters directly.
result POPLIN achieves state-of-the-art performance in MuJoCo benchmarks, 3x more sample efficient.
Bayesian model-based reinforcement learning is a formally elegant approach to learning optimal behaviour under model uncertainty, trading off exploration and exploitation in an ideal way. Unfortunately, finding the resulting Bayes-optimal policies is notoriously taxing, since the search space becomes enormous. In this …
We present an algorithm for model-based reinforcement learning that combines Bayesian neural networks (BNNs) with random roll-outs and stochastic optimization for policy learning. The BNNs are trained by minimizing α α α -divergences, allowing us to capture complicated statistical patterns in the transition dynamics, e.g.…
Proposes DGCN with trajectory sampling for data-efficient policy search in MBRL.
problem Improving data efficiency in model-based reinforcement learning.
method Combines trajectory sampling and DGCN for uncertainty propagation in probabilistic world models.
result Improves sample-efficiency over other uncertainty propagation methods and probabilistic models.
We consider two active binary-classification problems with atypical objectives. In the first, active search, our goal is to actively uncover as many members of a given class as possible. In the second, active surveying, our goal is to actively query points to ultimately predict the proportion of a given class. Numerous…
Data-driven decision-making often overestimates benefits due to the winner's curse.
problem Accurate policy evaluation in data-driven decision-making.
method Model-based policy evaluation using estimated models from data.
result Model-based methods can produce large, spurious reported benefits even when true effects are zero.
POMBU improves model-based RL's asymptotic performance by estimating and using uncertainty.
problem Model-based reinforcement learning struggles with model errors, leading to suboptimal performance.
method POMBU uses estimated uncertainty to optimize policies conservatively, improving asymptotic performance.
result POMBU outperforms existing methods in sample efficiency and asymptotic performance.
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.
The study compares reinforcement learning models and finds model-based approaches superior for complex MDPs.
problem Complexity of optimal Q-functions and policies in MDPs exceeds dynamics, hindering model-free methods.
method Theoretical analysis and empirical testing of neural network expressivity for policies, Q-functions, and dynamics.
result Model-based planning yields better policies for complex MDPs, improving performance on MuJoCo tasks.
Bayesian regularization improves policy performance in noisy MDPs.
problem Suboptimal policies from estimated model parameters.
method Bayesian regularization of MDP objective function with prior information.
result Regularized policies show better robustness against model noise.
MoMA improves model-based RL by using unrestricted policy classes.
problem Limited sample efficiency and generalizability in model-based offline RL.
method Model-based mirror ascent algorithm with general function approximations.
result Theoretical guarantees and practical implementation of MoMA.
Reduces policy space complexity for reinforcement learning.
problem Efficiency in exploring vast policy spaces in reinforcement learning.
method Uses Rényi divergence and l 1 l_1 l 1 norm to determine sample size for accurate policy approximation. result Established error bounds for sample size requirements in model-based and model-free settings.
PGS uses neural networks to improve policies online without search trees.
problem Limited scalability of Monte Carlo Tree Search (MCTS) for high branching factor games.
method Adapts a neural network simulation policy via policy gradient updates, avoiding search trees.
result PGS achieves comparable performance to MCTS and defeats strong Hex agents.
Efficiently find near-optimal medical treatments with less trial and error.
problem Finding effective medical treatments through trial and error.
method Formalizes the problem, uses a causal inference framework, and proposes model-based dynamic programming and greedy algorithms.
result Our methods compare favorably to model-free reinforcement learning, offering a more transparent trade-off between search time and treatment efficacy.
Paper analyzes model usage in policy optimization, improving sample efficiency and performance.
problem Balancing ease of data generation with model bias in reinforcement learning.
method Formulated and analyzed model-based reinforcement learning algorithm with empirical model generalization.
result Simple model-based approach outperforms existing methods in sample efficiency and asymptotic performance.
Policy Prediction Network improves continuous control problems with model-free and model-based learning.
problem Improving sample complexity and performance in continuous control problems.
method Integrates model-free and model-based reinforcement learning, introduces implicit model-based learning for continuous action space.
result First to introduce implicit model-based learning to Policy Gradient algorithms for continuous action space.
Adapts model-based advice to stabilize black-box policies for nonlinear control.
problem Stabilizing machine-learned policies for nonlinear control with limited model information.
method Proposes an adaptive λ λ λ -confident policy to combine black-box and model-based advice. result Proves the stability of the adaptive λ λ λ -confident policy and its competitive ratio. VMBPO optimizes model and policy jointly using variational lower-bound.
problem Data efficiency in RL with biased simulated data.
method Formulate variational objective function, use EM, iteratively improve model and policy.
result VMBPO is more sample-efficient and robust than model-free algorithms.
Proposes a new framework to optimize policies while accounting for model uncertainty.
problem Model-based reinforcement learning's vulnerability to model bias and inefficiency.
method Uncertainty-aware model-based policy optimization framework.
result Significantly lower sample complexity and competitive asymptotic performance.
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.
New bounds assess policy evaluation under unobserved confounders, showing model-based methods are more effective.
problem Policy evaluation under unobserved confounders in uncertain causal environments.
method Developed worst-case bounds for sensitivity to unobserved confounders, demonstrating model-based methods are more effective.
result Model-based approaches with robust MDPs provide sharper lower bounds for policy evaluation.
MB-MPO meta-learns a policy to adapt quickly to model ensembles, improving robustness and performance.
problem Challenges in learning accurate dynamics models for model-based reinforcement learning.
method Model-Based Meta-Policy-Optimization (MB-MPO) using an ensemble of learned dynamic models.
result MB-MPO achieves asymptotic performance similar to model-free methods with less experience and robustness to model imperfections.
M3PO improves model-based meta-RL with theoretical guarantees.
problem Improving sample efficiency in multi-task RL with theoretical guarantees.
method Extending Janner et al. (2019) theorems, proposing M3PO with performance guarantees.
result M3PO outperforms existing methods in continuous-control benchmarks.
This study evaluates cluster search algorithms using Gaussian mixture models.
problem Determining the optimal number of clusters in data sets generated by Gaussian mixture models.
method Examined centroid- and model-based cluster search algorithms in various cases.
result Model-based algorithms are more robust to cluster overlap and covariance type than centroid-based methods.
Simple model-based reinforcement learning outperforms model-free methods in complex tasks.
problem Lagging performance of model-based reinforcement learning agents in non-trivial environments.
method Combining soft value estimates with stochastic value gradients.
result Simple model-based agents achieve state-of-the-art results in a high-dimensional humanoid control task.
A framework schedules hyperparameters for model-based reinforcement learning, improving performance.
problem Inadequate scheduling of hyperparameters in model-based reinforcement learning.
method Theoretical analysis and AutoMBPO framework to automatically schedule real data ratio and other hyperparameters.
result Training with hyperparameters scheduled by AutoMBPO significantly improves performance.
Trust-region methods and natural gradients are equivalent in certain policy search scenarios.
problem Improving policy search methods in continuous control tasks.
method Introducing compatible policy search (COPOS) that uses natural parameterization and compatible value function approximation to control entropy loss.
result COPOS yields state-of-the-art results in challenging tasks and reduces entropy loss.
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.
MOPO optimizes offline RL by penalizing dynamics uncertainty.
problem Learning policies from offline data with distributional shift.
method Modify model-based RL to avoid distributional shift.
result MOPO outperforms model-free and standard model-based RL.
SAVE combines Q-learning and MCTS with amortized value estimates for improved performance.
problem Combining model-free Q-learning and model-based MCTS for efficient learning and planning.
method SAVE uses a learned prior to guide MCTS, which estimates improved state-action values. These estimates are used to update the prior, creating a cooperative relationship between learning and search.
result SAVE achieves higher rewards with fewer training steps and strong performance with small search budgets.
Autonomous learning has been a promising direction in control and robotics for more than a decade since data-driven learning allows to reduce the amount of engineering knowledge, which is otherwise required. However, autonomous reinforcement learning (RL) approaches typically require many interactions with the system t…
Bayesian approach for policy search in stochastic domains.
problem Policy search in stochastic domains.
method Nested probabilistic programs, Lightweight Metropolis-Hastings (LMH) adaptation.
result Similar quality policies learned with simpler algorithm.
Greedy policies in model-based RL achieve tight regret bounds without full planning.
problem Achieving efficient RL algorithms in MDP settings.
method Using greedy policies for 1-step planning in model-based RL.
result Greedy policies achieve i l d e O ( H S A T ) ilde{\mathcal{O}}(\sqrt{HSAT}) i l d e O ( H S A T ) regret bounds. Model-based RL with adversarial training for efficient recommendation policies.
problem Expensive model learning in model-free RL for recommender systems.
method Generative adversarial network for offline policy learning, discriminator for reward scaling and model bias reduction.
result Effective policy learning from offline and generated data, reducing bias in the learned model.
A new search-control strategy improves Dyna's efficiency.
problem Improving sample efficiency in model-based reinforcement learning.
method Proposes a novel search-control strategy by sampling high frequency regions of the value function.
result Empirically shows that high frequency regions require more samples to approximate, suggesting a better search-control strategy.