PyTorchKR Papers

최신 논문

총 13,741편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2403.02777

A Zero-Shot Reinforcement Learning Strategy for Autonomous Guidewire Navigation

Purpose: The treatment of cardiovascular diseases requires complex and challenging navigation of a guidewire and catheter. This often leads to lengthy interventions during which the patient and clinician are exposed to X-ray radiation. Deep Reinforcement Learning approaches have shown promise in learning this task and may be the key to automating catheter navigation during robotized interventions. Yet, existing training methods show limited capabilities at generalizing to unseen vascular anatomies, requiring to be retrained each time the geometry changes. Methods: In this paper, we propose a zero-shot learning strategy for three-dimensional autonomous endovascular navigation. Using a very small training set of branching patterns, our reinforcement learning algorithm is able to learn a control that can then be applied to unseen vascular anatomies without retraining. Results: We demonstrate our method on 4 different vascular systems, with an average success rate of 95% at reaching random targets on these anatomies. Our strategy is also computationally efficient, allowing the training of our controller to be performed in only 2 hours. Conclusion: Our training method proved its ability to navigate unseen geometries with different characteristics, thanks to a nearly shape-invariant observation space.

arXiv:2403.02475

Enhancing LLM Safety via Constrained Direct Preference Optimization

The rapidly increasing capabilities of large language models (LLMs) raise an urgent need to align AI systems with diverse human preferences to simultaneously enhance their usefulness and safety, despite the often conflicting nature of these goals. To address this important problem, a promising approach is to enforce a safety constraint at the fine-tuning stage through a constrained Reinforcement Learning from Human Feedback (RLHF) framework. This approach, however, is computationally expensive and often unstable. In this work, we introduce Constrained DPO (C-DPO), a novel extension of the recently proposed Direct Preference Optimization (DPO) approach for fine-tuning LLMs that is both efficient and lightweight. By integrating dual gradient descent and DPO, our method identifies a nearly optimal trade-off between helpfulness and harmlessness without using reinforcement learning. Empirically, our approach provides a safety guarantee to LLMs that is missing in DPO while achieving significantly higher rewards under the same safety constraint compared to a recently proposed safe RLHF approach. Warning: This paper contains example data that may be offensive or harmful.

arXiv:2403.01605

Towards Provable Log Density Policy Gradient

Policy gradient methods are a vital ingredient behind the success of modern reinforcement learning. Modern policy gradient methods, although successful, introduce a residual error in gradient estimation. In this work, we argue that this residual term is significant and correcting for it could potentially improve sample-complexity of reinforcement learning methods. To that end, we propose log density gradient to estimate the policy gradient, which corrects for this residual error term. Log density gradient method computes policy gradient by utilising the state-action discounted distributional formulation. We first present the equations needed to exactly find the log density gradient for a tabular Markov Decision Processes (MDPs). For more complex environments, we propose a temporal difference (TD) method that approximates log density gradient by utilizing backward on-policy samples. Since backward sampling from a Markov chain is highly restrictive we also propose a min-max optimization that can approximate log density gradient using just on-policy samples. We also prove uniqueness, and convergence under linear function approximation, for this min-max optimization. Finally, we show that the sample complexity of our min-max optimization to be of the order of $m^{-1/2}$, where $m$ is the number of on-policy samples. We also demonstrate a proof-of-concept for our log density gradient method on gridworld environment, and observe that our method is able to improve upon the classical policy gradient method by a clear margin, thus indicating a promising novel direction to develop reinforcement learning algorithms that require fewer samples.

arXiv:2403.02338

Twisting Lids Off with Two Hands

Manipulating objects with two multi-fingered hands has been a long-standing challenge in robotics, due to the contact-rich nature of many manipulation tasks and the complexity inherent in coordinating a high-dimensional bimanual system. In this work, we share novel insights into physical modeling, real-time perception, and reward design that enable policies trained in simulation using deep reinforcement learning (RL) to be effectively and efficiently transferred to the real world. Specifically, we consider the problem of twisting lids of various bottle-like objects with two hands, demonstrating policies with generalization capabilities across a diverse set of unseen objects as well as dynamic and dexterous behaviors. To the best of our knowledge, this is the first sim-to-real RL system that enables such capabilities on bimanual multi-fingered hands.

arXiv:2403.02290

Koopman-Assisted Reinforcement Learning

The Bellman equation and its continuous form, the Hamilton-Jacobi-Bellman (HJB) equation, are ubiquitous in reinforcement learning (RL) and control theory. However, these equations quickly become intractable for systems with high-dimensional states and nonlinearity. This paper explores the connection between the data-driven Koopman operator and Markov Decision Processes (MDPs), resulting in the development of two new RL algorithms to address these limitations. We leverage Koopman operator techniques to lift a nonlinear system into new coordinates where the dynamics become approximately linear, and where HJB-based methods are more tractable. In particular, the Koopman operator is able to capture the expectation of the time evolution of the value function of a given system via linear dynamics in the lifted coordinates. By parameterizing the Koopman operator with the control actions, we construct a ``Koopman tensor'' that facilitates the estimation of the optimal value function. Then, a transformation of Bellman's framework in terms of the Koopman tensor enables us to reformulate two max-entropy RL algorithms: soft value iteration and soft actor-critic (SAC). This highly flexible framework can be used for deterministic or stochastic systems as well as for discrete or continuous-time dynamics. Finally, we show that these Koopman Assisted Reinforcement Learning (KARL) algorithms attain state-of-the-art (SOTA) performance with respect to traditional neural network-based SAC and linear quadratic regulator (LQR) baselines on four controlled dynamical systems: a linear state-space system, the Lorenz system, fluid flow past a cylinder, and a double-well potential with non-isotropic stochastic forcing.

arXiv:2403.03185공식 코드 · Papers with Code

Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking

Because it is difficult to precisely specify complex objectives, reinforcement learning policies are often optimized using proxy reward functions that only approximate the true goal. However, optimizing proxy rewards frequently leads to reward hacking: the optimized reward function ceases to be a good proxy and the resulting policy performs poorly with respect to the unspecified true reward. Principled solutions to reward hacking have been impeded by the lack of a good definition for the problem. To address this gap, we introduce a definition of reward hacking based on the correlation between proxy and true rewards for states and actions seen by a "base policy" that breaks down under optimization. We show that this definition captures reward hacking behavior across several realistic settings, including in reinforcement learning from human feedback (RLHF). Using our formulation, we show theoretically that regularization to the base policy can effectively prevent reward hacking. While the current practice in RLHF applies a KL penalty between action distributions for this purpose, our theory suggests regularizing the $\chi^2$ divergence between the policies' occupancy measures can be more effective. We intuitively show the benefits of this type of regularization and demonstrate that it better mitigates reward hacking in practice across four realistic settings, including RLHF. Our code is available at https://github.com/cassidylaidlaw/orpo.

arXiv:2403.03020공식 코드 · Papers with Code

SplAgger: Split Aggregation for Meta-Reinforcement Learning

A core ambition of reinforcement learning (RL) is the creation of agents capable of rapid learning in novel tasks. Meta-RL aims to achieve this by directly learning such agents. Black box methods do so by training off-the-shelf sequence models end-to-end. By contrast, task inference methods explicitly infer a posterior distribution over the unknown task, typically using distinct objectives and sequence models designed to enable task inference. Recent work has shown that task inference methods are not necessary for strong performance. However, it remains unclear whether task inference sequence models are beneficial even when task inference objectives are not. In this paper, we present evidence that task inference sequence models are indeed still beneficial. In particular, we investigate sequence models with permutation invariant aggregation, which exploit the fact that, due to the Markov property, the task posterior does not depend on the order of data. We empirically confirm the advantage of permutation invariant sequence models without the use of task inference objectives. However, we also find, surprisingly, that there are multiple conditions under which permutation variance remains useful. Therefore, we propose SplAgger, which uses both permutation variant and invariant components to achieve the best of both worlds, outperforming all baselines evaluated on continuous control and memory environments. Code is provided at https://github.com/jacooba/hyper.

arXiv:2403.02635공식 코드 · Papers with Code

PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning

Training for multi-agent reinforcement learning(MARL) is a time-consuming process caused by distribution shift of each agent. One drawback is that strategy of each agent in MARL is independent but actually in cooperation. Thus, a vertical issue in multi-agent reinforcement learning is how to efficiently accelerate training process. To address this problem, current research has leveraged a centralized function(CF) across multiple agents to learn contribution of the team reward for each agent. However, CF based methods introduce joint error from other agents in estimation of value network. In so doing, inspired by federated learning, we propose three simple novel approaches called Average Periodically Parameter Sharing(A-PPS), Reward-Scalability Periodically Parameter Sharing(RS-PPS) and Partial Personalized Periodically Parameter Sharing(PP-PPS) mechanism to accelerate training of MARL. Agents share Q-value network periodically during the training process. Agents which has same identity adapt collected reward as scalability and update partial neural network during period to share different parameters. We apply our approaches in classical MARL method QMIX and evaluate our approaches on various tasks in StarCraft Multi-Agent Challenge(SMAC) environment. Performance of numerical experiments yield enormous enhancement, with an average improvement of 10\%-30\%, and enable to win tasks that QMIX cannot. Our code can be downloaded from https://github.com/ColaZhang22/PPS-QMIX

arXiv:2403.00282

Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning

In many real-world applications, a reinforcement learning (RL) agent should consider multiple objectives and adhere to safety guidelines. To address these considerations, we propose a constrained multi-objective RL algorithm named Constrained Multi-Objective Gradient Aggregator (CoMOGA). In the field of multi-objective optimization, managing conflicts between the gradients of the multiple objectives is crucial to prevent policies from converging to local optima. It is also essential to efficiently handle safety constraints for stable training and constraint satisfaction. We address these challenges straightforwardly by treating the maximization of multiple objectives as a constrained optimization problem (COP), where the constraints are defined to improve the original objectives. Existing safety constraints are then integrated into the COP, and the policy is updated using a linear approximation, which ensures the avoidance of gradient conflicts. Despite its simplicity, CoMOGA guarantees optimal convergence in tabular settings. Through various experiments, we have confirmed that preventing gradient conflicts is critical, and the proposed method achieves constraint satisfaction across all tasks.

arXiv:2403.01112공식 코드 · Papers with Code

Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning

In cooperative multi-agent reinforcement learning (MARL), agents aim to achieve a common goal, such as defeating enemies or scoring a goal. Existing MARL algorithms are effective but still require significant learning time and often get trapped in local optima by complex tasks, subsequently failing to discover a goal-reaching policy. To address this, we introduce Efficient episodic Memory Utilization (EMU) for MARL, with two primary objectives: (a) accelerating reinforcement learning by leveraging semantically coherent memory from an episodic buffer and (b) selectively promoting desirable transitions to prevent local convergence. To achieve (a), EMU incorporates a trainable encoder/decoder structure alongside MARL, creating coherent memory embeddings that facilitate exploratory memory recall. To achieve (b), EMU introduces a novel reward structure called episodic incentive based on the desirability of states. This reward improves the TD target in Q-learning and acts as an additional incentive for desirable transitions. We provide theoretical support for the proposed incentive and demonstrate the effectiveness of EMU compared to conventional episodic control. The proposed method is evaluated in StarCraft II and Google Research Football, and empirical results indicate further performance improvement over state-of-the-art methods.

arXiv:2403.01059

Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL)

Machine-learning paradigms such as imitation learning and reinforcement learning can generate highly performant agents in a variety of complex environments. However, commonly used methods require large quantities of data and/or a known reward function. This paper presents a method called Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL) that employs a novel reward structure to improve the performance of imitation-learning agents that have access to only a handful of expert demonstrations. CMZ-DRIL uses reinforcement learning to minimize uncertainty among an ensemble of agents trained to model the expert demonstrations. This method does not use any environment-specific rewards, but creates a continuous and mean-zero reward function from the action disagreement of the agent ensemble. As demonstrated in a waypoint-navigation environment and in two MuJoCo environments, CMZ-DRIL can generate performant agents that behave more similarly to the expert than primary previous approaches in several key metrics.

arXiv:2403.00673공식 코드 · Papers with Code

Snapshot Reinforcement Learning: Leveraging Prior Trajectories for Efficiency

Deep reinforcement learning (DRL) algorithms require substantial samples and computational resources to achieve higher performance, which restricts their practical application and poses challenges for further development. Given the constraint of limited resources, it is essential to leverage existing computational work (e.g., learned policies, samples) to enhance sample efficiency and reduce the computational resource consumption of DRL algorithms. Previous works to leverage existing computational work require intrusive modifications to existing algorithms and models, designed specifically for specific algorithms, lacking flexibility and universality. In this paper, we present the Snapshot Reinforcement Learning (SnapshotRL) framework, which enhances sample efficiency by simply altering environments, without making any modifications to algorithms and models. By allowing student agents to choose states in teacher trajectories as the initial state to sample, SnapshotRL can effectively utilize teacher trajectories to assist student agents in training, allowing student agents to explore a larger state space at the early training phase. We propose a simple and effective SnapshotRL baseline algorithm, S3RL, which integrates well with existing DRL algorithms. Our experiments demonstrate that integrating S3RL with TD3, SAC, and PPO algorithms on the MuJoCo benchmark significantly improves sample efficiency and average return, without extra samples and additional computational resources.

arXiv:2403.00991

SELFI: Autonomous Self-Improvement with Reinforcement Learning for Social Navigation

Autonomous self-improving robots that interact and improve with experience are key to the real-world deployment of robotic systems. In this paper, we propose an online learning method, SELFI, that leverages online robot experience to rapidly fine-tune pre-trained control policies efficiently. SELFI applies online model-free reinforcement learning on top of offline model-based learning to bring out the best parts of both learning paradigms. Specifically, SELFI stabilizes the online learning process by incorporating the same model-based learning objective from offline pre-training into the Q-values learned with online model-free reinforcement learning. We evaluate SELFI in multiple real-world environments and report improvements in terms of collision avoidance, as well as more socially compliant behavior, measured by a human user study. SELFI enables us to quickly learn useful robotic behaviors with less human interventions such as pre-emptive behavior for the pedestrians, collision avoidance for small and transparent objects, and avoiding travel on uneven floor surfaces. We provide supplementary videos to demonstrate the performance of our fine-tuned policy on our project page.

arXiv:2403.00993

On the Role of Information Structure in Reinforcement Learning for Partially-Observable Sequential Teams and Games

In a sequential decision-making problem, the information structure is the description of how events in the system occurring at different points in time affect each other. Classical models of reinforcement learning (e.g., MDPs, POMDPs) assume a simple and highly regular information structure, while more general models like predictive state representations do not explicitly model the information structure. By contrast, real-world sequential decision-making problems typically involve a complex and time-varying interdependence of system variables, requiring a rich and flexible representation of information structure. In this paper, we formalize a novel reinforcement learning model which explicitly represents the information structure. We then use this model to carry out an information-structural analysis of the statistical hardness of general sequential decision-making problems, obtaining a characterization via a graph-theoretic quantity of the DAG representation of the information structure. We prove an upper bound on the sample complexity of learning a general sequential decision-making problem in terms of its information structure by exhibiting an algorithm achieving the upper bound. This recovers known tractability results and gives a novel perspective on reinforcement learning in general sequential decision-making problems, providing a systematic way of identifying new tractable classes of problems.

arXiv:2403.00930

Scale-free Adversarial Reinforcement Learning

This paper initiates the study of scale-free learning in Markov Decision Processes (MDPs), where the scale of rewards/losses is unknown to the learner. We design a generic algorithmic framework, \underline{S}cale \underline{C}lipping \underline{B}ound (\texttt{SCB}), and instantiate this framework in both the adversarial Multi-armed Bandit (MAB) setting and the adversarial MDP setting. Through this framework, we achieve the first minimax optimal expected regret bound and the first high-probability regret bound in scale-free adversarial MABs, resolving an open problem raised in \cite{hadiji2023adaptation}. On adversarial MDPs, our framework also give birth to the first scale-free RL algorithm with a $\tilde{\mathcal{O}}(\sqrt{T})$ high-probability regret guarantee.

arXiv:2402.19275

Adaptive Testing Environment Generation for Connected and Automated Vehicles with Dense Reinforcement Learning

The assessment of safety performance plays a pivotal role in the development and deployment of connected and automated vehicles (CAVs). A common approach involves designing testing scenarios based on prior knowledge of CAVs (e.g., surrogate models), conducting tests in these scenarios, and subsequently evaluating CAVs' safety performances. However, substantial differences between CAVs and the prior knowledge can significantly diminish the evaluation efficiency. In response to this issue, existing studies predominantly concentrate on the adaptive design of testing scenarios during the CAV testing process. Yet, these methods have limitations in their applicability to high-dimensional scenarios. To overcome this challenge, we develop an adaptive testing environment that bolsters evaluation robustness by incorporating multiple surrogate models and optimizing the combination coefficients of these surrogate models to enhance evaluation efficiency. We formulate the optimization problem as a regression task utilizing quadratic programming. To efficiently obtain the regression target via reinforcement learning, we propose the dense reinforcement learning method and devise a new adaptive policy with high sample efficiency. Essentially, our approach centers on learning the values of critical scenes displaying substantial surrogate-to-real gaps. The effectiveness of our method is validated in high-dimensional overtaking scenarios, demonstrating that our approach achieves notable evaluation efficiency.

arXiv:2402.19212

Deep Reinforcement Learning: A Convex Optimization Approach

In this paper, we consider reinforcement learning of nonlinear systems with continuous state and action spaces. We present an episodic learning algorithm, where we for each episode use convex optimization to find a two-layer neural network approximation of the optimal $Q$-function. The convex optimization approach guarantees that the weights calculated at each episode are optimal, with respect to the given sampled states and actions of the current episode. For stable nonlinear systems, we show that the algorithm converges and that the converging parameters of the trained neural network can be made arbitrarily close to the optimal neural network parameters. In particular, if the regularization parameter in the training phase is given by $\rho$, then the parameters of the trained neural network converge to $w$, where the distance between $w$ and the optimal parameters $w^\star$ is bounded by $\mathcal{O}(\rho)$. That is, when the number of episodes goes to infinity, there exists a constant $C$ such that \[ \|w-w^\star\| \le C\rho. \] In particular, our algorithm converges arbitrarily close to the optimal neural network parameters as the regularization parameter goes to zero. As a consequence, our algorithm converges fast due to the polynomial-time convergence of convex optimization algorithms.

arXiv:2402.18836공식 코드 · Papers with Code

A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations

This paper investigates how to incorporate expert observations (without explicit information on expert actions) into a deep reinforcement learning setting to improve sample efficiency. First, we formulate an augmented policy loss combining a maximum entropy reinforcement learning objective with a behavioral cloning loss that leverages a forward dynamics model. Then, we propose an algorithm that automatically adjusts the weights of each component in the augmented loss function. Experiments on a variety of continuous control tasks demonstrate that the proposed algorithm outperforms various benchmarks by effectively utilizing available expert observations.

arXiv:2402.18762

Disentangling the Causes of Plasticity Loss in Neural Networks

Underpinning the past decades of work on the design, initialization, and optimization of neural networks is a seemingly innocuous assumption: that the network is trained on a \textit{stationary} data distribution. In settings where this assumption is violated, e.g.\ deep reinforcement learning, learning algorithms become unstable and brittle with respect to hyperparameters and even random seeds. One factor driving this instability is the loss of plasticity, meaning that updating the network's predictions in response to new information becomes more difficult as training progresses. While many recent works provide analyses and partial solutions to this phenomenon, a fundamental question remains unanswered: to what extent do known mechanisms of plasticity loss overlap, and how can mitigation strategies be combined to best maintain the trainability of a network? This paper addresses these questions, showing that loss of plasticity can be decomposed into multiple independent mechanisms and that, while intervening on any single mechanism is insufficient to avoid the loss of plasticity in all cases, intervening on multiple mechanisms in conjunction results in highly robust learning algorithms. We show that a combination of layer normalization and weight decay is highly effective at maintaining plasticity in a variety of synthetic nonstationary learning tasks, and further demonstrate its effectiveness on naturally arising nonstationarities, including reinforcement learning in the Arcade Learning Environment.

arXiv:2312.09468

Safe Reinforcement Learning in a Simulated Robotic Arm

Reinforcement learning (RL) agents need to explore their environments in order to learn optimal policies. In many environments and tasks, safety is of critical importance. The widespread use of simulators offers a number of advantages, including safe exploration which will be inevitable in cases when RL systems need to be trained directly in the physical environment (e.g. in human-robot interaction). The popular Safety Gym library offers three mobile agent types that can learn goal-directed tasks while considering various safety constraints. In this paper, we extend the applicability of safe RL algorithms by creating a customized environment with Panda robotic arm where Safety Gym algorithms can be tested. We performed pilot experiments with the popular PPO algorithm comparing the baseline with the constrained version and show that the constrained version is able to learn the equally good policy while better complying with safety constraints and taking longer training time as expected.