arXiv research

New hybrid RL algorithm outperforms model-free and model-based methods.

FORK improves model-free reinforcement learning performance.

Simple object representations improve model-free RL performance.

Paper shows intrinsic motivation boosts exploration efficiency in HRL.

Unified reinforcement learning methods using hybrid inference.

Two new algorithms improve model-free RL for infinite-horizon MDPs.

Simple model-based reinforcement learning outperforms model-free methods in complex tasks.

Simple image augmentation boosts deep RL from pixels.

Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagined data coupled with a notion of model uncertainty to accelerate the learning of c…

Efficient Reinforcement Learning usually takes advantage of demonstration or good exploration strategy. By applying posterior sampling in model-free RL under the hypothesis of GP, we propose Gaussian Process Posterior Sampling Reinforcement Learning(GPPSTD) algorithm in continuous state space, giving theoretical justif…

Improved model-free reinforcement learning with decision-estimation coefficient.

New model-free DR-RL algorithm with finite sample complexity.

Policy Prediction Network improves continuous control problems with model-free and model-based learning.

UCB-Advantage learns MDPs with $O(\sqrt{H^2SAT})$ regret.

Improves sample efficiency in RL by matching model-based gradients.

A new model-free algorithm achieves near-optimal regret for infinite-horizon MDPs.

Improved model-free RL from images with stable training.

We provide the first solution for model-free reinforcement learning of ω-regular objectives for Markov decision processes (MDPs). We present a constructive reduction from the almost-sure satisfaction of ω-regular objectives to an almost- sure reachability problem and extend this technique to learning how to control an …

The OGY method is one of control methods for a chaotic system. In the method, we have to calculate a stabilizing periodic orbit embedded in its chaotic attractor. Thus, we cannot use this method in the case where a precise mathematical model of the chaotic system cannot be identified. In this case, the delayed feedback…

PPOPT uses pretraining to speed up reinforcement learning in physics simulations.

Model-free Reinforcement Learning (RL) algorithms such as Q-learning [Watkins, Dayan 92] have been widely used in practice and can achieve human level performance in applications such as video games [Mnih et al. 15]. Recently, equipped with the idea of optimism in the face of uncertainty, Q-learning algorithms [Jin, Al…

This work proposes robust reinforcement learning methods using both offline and online data.

New model-free algorithms learn representations for low-rank MDPs efficiently.

New algorithms for model selection in off-policy evaluation of reinforcement learning.

Optimizes control of noisy discrete systems without system matrix knowledge.

New algorithm learns optimal policies with minimal memory and time.

Improved model-free RL algorithm with reduced sample complexity.

Robotic table tennis learns efficient policies to return balls at 100Hz.

Discovering and exploiting the causal structure in the environment is a crucial challenge for intelligent agents. Here we explore whether causal reasoning can emerge via meta-reinforcement learning. We train a recurrent network with model-free reinforcement learning to solve a range of problems that each contain causal…

DREAM learns optimal strategies in imperfect games without needing a simulator.

Unified Latent Dynamics unifies model-free and model-based reinforcement learning.

The study compares reinforcement learning models and finds model-based approaches superior for complex MDPs.

Integrating model-free and model-based approaches in reinforcement learning has the potential to achieve the high performance of model-free algorithms with low sample complexity. However, this is difficult because an imperfect dynamics model can degrade the performance of the learning algorithm, and in sufficiently com…

New algorithm borrows future randomness to stabilize model-free control.

The paper tackles model-based RL's inaccuracy issue by dynamically adjusting planning horizons.

Minimum attention improves reinforcement learning performance in high-dimensional dynamics.

We study an exploration method for model-free RL that generalizes the counter-based exploration bonus methods and takes into account long term exploratory value of actions rather than a single step look-ahead. We propose a model-free RL method that modifies Delayed Q-learning and utilizes the long-term exploration bonu…

Recent success in deep reinforcement learning for continuous control has been dominated by model-free approaches which, unlike model-based approaches, do not suffer from representational limitations in making assumptions about the world dynamics and model errors inevitable in complex domains. However, they require a lo…

A new method stabilizes deep reinforcement learning by using QGraphs to retain replay memory information.

Hybrid controller combines model-based and policy-based reinforcement learning.

Model-free reinforcement learning methods such as the Proximal Policy Optimization algorithm (PPO) have successfully applied in complex decision-making problems such as Atari games. However, these methods suffer from high variances and high sample complexity. On the other hand, model-based reinforcement learning method…

The paper tackles robust reinforcement learning with performance guarantees.

Combines model-based and model-free RL for better financial market performance.

Financial portfolio management is one of the problems that are most frequently encountered in the investment industry. Nevertheless, it is not widely recognized that both Kelly Criterion and Risk Parity collapse into Mean Variance under some conditions, which implies that a universal solution to the portfolio optimizat…

Model-based reinforcement learning (RL) algorithms can attain excellent sample efficiency, but often lag behind the best model-free algorithms in terms of asymptotic performance. This is especially true with high-capacity parametric function approximators, such as deep networks. In this paper, we study how to bridge th…

Model-free deep reinforcement learning has been shown to exhibit good performance in domains ranging from video games to simulated robotic manipulation and locomotion. However, model-free methods are known to perform poorly when the interaction time with the environment is limited, as is the case for most real-world ro…

Bayesian approach improves $\varepsilon$-greedy exploration in RL.

New algorithm improves RL performance across different environments.