Due to its training stability and strong expression, the diffusion model has attracted considerable attention in offline reinforcement learning. However, several challenges have also come with it: 1) The demand for a large number of diffusion steps makes the diffusion-model-based methods time inefficient and limits their applications in real-time control; 2) How to achieve policy improvement with accurate guidance for diffusion model-based policy is still an open problem. Inspired by the consistency model, we propose a novel time-efficiency method named Consistency Policy with Q-Learning (CPQL), which derives action from noise by a single step. By establishing a mapping from the reverse diffusion trajectories to the desired policy, we simultaneously address the issues of time efficiency and inaccurate guidance when updating diffusion model-based policy with the learned Q-function. We demonstrate that CPQL can achieve policy improvement with accurate guidance for offline reinforcement learning, and can be seamlessly extended for online RL tasks. Experimental results indicate that CPQL achieves new state-of-the-art performance on 11 offline and 21 online tasks, significantly improving inference speed by nearly 45 times compared to Diffusion-QL. We will release our code later.
Offline pretraining with a static dataset followed by online fine-tuning (offline-to-online, or OtO) is a paradigm well matched to a real-world RL deployment process. In this scenario, we aim to find the best-performing policy within a limited budget of online interactions. Previous work in the OtO setting has focused on correcting for bias introduced by the policy-constraint mechanisms of offline RL algorithms. Such constraints keep the learned policy close to the behavior policy that collected the dataset, but we show this can unnecessarily limit policy performance if the behavior policy is far from optimal. Instead, we forgo constraints and frame OtO RL as an exploration problem that aims to maximize the benefit of online data-collection. We first study the major online RL exploration methods based on intrinsic rewards and UCB in the OtO setting, showing that intrinsic rewards add training instability through reward-function modification, and UCB methods are myopic and it is unclear which learned-component's ensemble to use for action selection. We then introduce an algorithm for planning to go out-of-distribution (PTGOOD) that avoids these issues. PTGOOD uses a non-myopic planning procedure that targets exploration in relatively high-reward regions of the state-action space unlikely to be visited by the behavior policy. By leveraging concepts from the Conditional Entropy Bottleneck, PTGOOD encourages data collected online to provide new information relevant to improving the final deployment policy without altering rewards. We show empirically in several continuous control tasks that PTGOOD significantly improves agent returns during online fine-tuning and avoids the suboptimal policy convergence that many of our baselines exhibit in several environments.
Real-world reinforcement learning (RL) environments, whether in robotics or industrial settings, often involve non-visual observations and require not only efficient but also reliable and thus interpretable and flexible RL approaches. To improve efficiency, agents that perform state representation learning with auxiliary tasks have been widely studied in visual observation contexts. However, for real-world problems, dedicated representation learning modules that are decoupled from RL agents are more suited to meet requirements. This study compares common auxiliary tasks based on, to the best of our knowledge, the only decoupled representation learning method for low-dimensional non-visual observations. We evaluate potential improvements in sample efficiency and returns for environments ranging from a simple pendulum to a complex simulated robotics task. Our findings show that representation learning with auxiliary tasks only provides performance gains in sufficiently complex environments and that learning environment dynamics is preferable to predicting rewards. These insights can inform future development of interpretable representation learning approaches for non-visual observations and advance the use of RL solutions in real-world scenarios.
Imitation Learning from Observation (ILfO) is a setting in which a learner tries to imitate the behavior of an expert, using only observational data and without the direct guidance of demonstrated actions. In this paper, we re-examine optimal transport for IL, in which a reward is generated based on the Wasserstein distance between the state trajectories of the learner and expert. We show that existing methods can be simplified to generate a reward function without requiring learned models or adversarial learning. Unlike many other state-of-the-art methods, our approach can be integrated with any RL algorithm and is amenable to ILfO. We demonstrate the effectiveness of this simple approach on a variety of continuous control tasks and find that it surpasses the state of the art in the IlfO setting, achieving expert-level performance across a range of evaluation domains even when observing only a single expert trajectory without actions.
Text generation in image-based platforms, particularly for music-related content, requires precise control over text styles and the incorporation of emotional expression. However, existing approaches often need help to control the proportion of external factors in generated text and rely on discrete inputs, lacking continuous control conditions for desired text generation. This study proposes Continuous Parameterization for Controlled Text Generation (CPCTG) to overcome these limitations. Our approach leverages a Language Model (LM) as a style learner, integrating Semantic Cohesion (SC) and Emotional Expression Proportion (EEP) considerations. By enhancing the reward method and manipulating the CPCTG level, our experiments on playlist description and music topic generation tasks demonstrate significant improvements in ROUGE scores, indicating enhanced relevance and coherence in the generated text.
Neural ordinary differential equations (ODEs) are widely recognized as the standard for modeling physical mechanisms, which help to perform approximate inference in unknown physical or biological environments. In partially observable (PO) environments, how to infer unseen information from raw observations puzzled the agents. By using a recurrent policy with a compact context, context-based reinforcement learning provides a flexible way to extract unobservable information from historical transitions. To help the agent extract more dynamics-related information, we present a novel ODE-based recurrent model combines with model-free reinforcement learning (RL) framework to solve partially observable Markov decision processes (POMDPs). We experimentally demonstrate the efficacy of our methods across various PO continuous control and meta-RL tasks. Furthermore, our experiments illustrate that our method is robust against irregular observations, owing to the ability of ODEs to model irregularly-sampled time series.
In different wireless network scenarios, multiple network entities need to cooperate in order to achieve a common task with minimum delay and energy consumption. Future wireless networks mandate exchanging high dimensional data in dynamic and uncertain environments, therefore implementing communication control tasks becomes challenging and highly complex. Multi-agent reinforcement learning with emergent communication (EC-MARL) is a promising solution to address high dimensional continuous control problems with partially observable states in a cooperative fashion where agents build an emergent communication protocol to solve complex tasks. This paper articulates the importance of EC-MARL within the context of future 6G wireless networks, which imbues autonomous decision-making capabilities into network entities to solve complex tasks such as autonomous driving, robot navigation, flying base stations network planning, and smart city applications. An overview of EC-MARL algorithms and their design criteria are provided while presenting use cases and research opportunities on this emerging topic.
This paper considers the problem of the bearing-based formation control with disturbance rejection for a group of agents under the leader-follower structure. The disturbances are in the form of a trigonometric polynomial with arbitrary unknown amplitudes, unknown initial phases, and known or unknown frequencies. For the case of the known frequencies, we employ the canonical internal model to solve the problem, and, for the case of the unknown frequencies, we combine the canonical internal model and {some} distributed adaptive control technique to deal with the problem. It is noted that the existing results can only handle constant input disturbances by continuous control laws or disturbances with known {bounds} by discontinuous control laws. The first case is a special case of our result. The second case cannot cover our results because the bound of our disturbance is unknown. Moreover, our control law is smooth.
A key challenge in training generally-capable agents is the design of training tasks that facilitate broad generalization and robustness to environment variations. This challenge motivates the problem setting of Unsupervised Environment Design (UED), whereby a student agent trains on an adaptive distribution of tasks proposed by a teacher agent. A pioneering approach for UED is PAIRED, which uses reinforcement learning (RL) to train a teacher policy to design tasks from scratch, making it possible to directly generate tasks that are adapted to the agent's current capabilities. Despite its strong theoretical backing, PAIRED suffers from a variety of challenges that hinder its practical performance. Thus, state-of-the-art methods currently rely on curation and mutation rather than generation of new tasks. In this work, we investigate several key shortcomings of PAIRED and propose solutions for each shortcoming. As a result, we make it possible for PAIRED to match or exceed state-of-the-art methods, producing robust agents in several established challenging procedurally-generated environments, including a partially-observed maze navigation task and a continuous-control car racing environment. We believe this work motivates a renewed emphasis on UED methods based on learned models that directly generate challenging environments, potentially unlocking more open-ended RL training and, as a result, more general agents.
Discrete reinforcement learning (RL) algorithms have demonstrated exceptional performance in solving sequential decision tasks with discrete action spaces, such as Atari games. However, their effectiveness is hindered when applied to continuous control problems due to the challenge of dimensional explosion. In this paper, we present the Soft Decomposed Policy-Critic (SDPC) architecture, which combines soft RL and actor-critic techniques with discrete RL methods to overcome this limitation. SDPC discretizes each action dimension independently and employs a shared critic network to maximize the soft $Q$-function. This novel approach enables SDPC to support two types of policies: decomposed actors that lead to the Soft Decomposed Actor-Critic (SDAC) algorithm, and decomposed $Q$-networks that generate Boltzmann soft exploration policies, resulting in the Soft Decomposed-Critic Q (SDCQ) algorithm. Through extensive experiments, we demonstrate that our proposed approach outperforms state-of-the-art continuous RL algorithms in a variety of continuous control tasks, including Mujoco's Humanoid and Box2d's BipedalWalker. These empirical results validate the effectiveness of the SDPC architecture in addressing the challenges associated with continuous control.
Quantifying uncertainty about a policy's long-term performance is important to solve sequential decision-making tasks. We study the problem from a model-based Bayesian reinforcement learning perspective, where the goal is to learn the posterior distribution over value functions induced by parameter (epistemic) uncertainty of the Markov decision process. Previous work restricts the analysis to a few moments of the distribution over values or imposes a particular distribution shape, e.g., Gaussians. Inspired by distributional reinforcement learning, we introduce a Bellman operator whose fixed-point is the value distribution function. Based on our theory, we propose Epistemic Quantile-Regression (EQR), a model-based algorithm that learns a value distribution function. We combine EQR with soft actor-critic (SAC) for policy optimization with an arbitrary differentiable objective function of the learned value distribution. Evaluation across several continuous-control tasks shows performance benefits with respect to both model-based and model-free algorithms. The code is available at https://github.com/boschresearch/dist-mbrl.
QDax is an open-source library with a streamlined and modular API for Quality-Diversity (QD) optimization algorithms in Jax. The library serves as a versatile tool for optimization purposes, ranging from black-box optimization to continuous control. QDax offers implementations of popular QD, Neuroevolution, and Reinforcement Learning (RL) algorithms, supported by various examples. All the implementations can be just-in-time compiled with Jax, facilitating efficient execution across multiple accelerators, including GPUs and TPUs. These implementations effectively demonstrate the framework's flexibility and user-friendliness, easing experimentation for research purposes. Furthermore, the library is thoroughly documented and tested with 95\% coverage.
Goal-Conditioned Hierarchical Reinforcement Learning (GCHRL) is a promising paradigm to address the exploration-exploitation dilemma in reinforcement learning. It decomposes the source task into subgoal conditional subtasks and conducts exploration and exploitation in the subgoal space. The effectiveness of GCHRL heavily relies on subgoal representation functions and subgoal selection strategy. However, existing works often overlook the temporal coherence in GCHRL when learning latent subgoal representations and lack an efficient subgoal selection strategy that balances exploration and exploitation. This paper proposes HIerarchical reinforcement learning via dynamically building Latent Landmark graphs (HILL) to overcome these limitations. HILL learns latent subgoal representations that satisfy temporal coherence using a contrastive representation learning objective. Based on these representations, HILL dynamically builds latent landmark graphs and employs a novelty measure on nodes and a utility measure on edges. Finally, HILL develops a subgoal selection strategy that balances exploration and exploitation by jointly considering both measures. Experimental results demonstrate that HILL outperforms state-of-the-art baselines on continuous control tasks with sparse rewards in sample efficiency and asymptotic performance. Our code is available at https://github.com/papercode2022/HILL.
Deploying reinforcement learning (RL) systems requires robustness to uncertainty and model misspecification, yet prior robust RL methods typically only study noise introduced independently across time. However, practical sources of uncertainty are usually coupled across time. We formally introduce temporally-coupled perturbations, presenting a novel challenge for existing robust RL methods. To tackle this challenge, we propose GRAD, a novel game-theoretic approach that treats the temporally-coupled robust RL problem as a partially observable two-player zero-sum game. By finding an approximate equilibrium within this game, GRAD optimizes for general robustness against temporally-coupled perturbations. Experiments on continuous control tasks demonstrate that, compared with prior methods, our approach achieves a higher degree of robustness to various types of attacks on different attack domains, both in settings with temporally-coupled perturbations and decoupled perturbations.
Model-based reinforcement learning (RL) has demonstrated remarkable successes on a range of continuous control tasks due to its high sample efficiency. To save the computation cost of conducting planning online, recent practices tend to distill optimized action sequences into an RL policy during the training phase. Although the distillation can incorporate both the foresight of planning and the exploration ability of RL policies, the theoretical understanding of these methods is yet unclear. In this paper, we extend the policy improvement step of Soft Actor-Critic (SAC) by developing an approach to distill from model-based planning to the policy. We then demonstrate that such an approach of policy improvement has a theoretical guarantee of monotonic improvement and convergence to the maximum value defined in SAC. We discuss effective design choices and implement our theory as a practical algorithm -- Model-based Planning Distilled to Policy (MPDP) -- that updates the policy jointly over multiple future time steps. Extensive experiments show that MPDP achieves better sample efficiency and asymptotic performance than both model-free and model-based planning algorithms on six continuous control benchmark tasks in MuJoCo.
We leverage the fast physics simulator, MuJoCo to run tasks in a continuous control environment and reveal details like the observation space, action space, rewards, etc. for each task. We benchmark value-based methods for continuous control by comparing Q-learning and SARSA through a discretization approach, and using them as baselines, progressively moving into one of the state-of-the-art deep policy gradient method DDPG. Over a large number of episodes, Qlearning outscored SARSA, but DDPG outperformed both in a small number of episodes. Lastly, we also fine-tuned the model hyper-parameters expecting to squeeze more performance but using lesser time and resources. We anticipated that the new design for DDPG would vastly improve performance, yet after only a few episodes, we were able to achieve decent average rewards. We expect to improve the performance provided adequate time and computational resources.
For problems in image processing and many other fields, a large class of effective neural networks has encoder-decoder-based architectures. Although these networks have made impressive performances, mathematical explanations of their architectures are still underdeveloped. In this paper, we study the encoder-decoder-based network architecture from the algorithmic perspective and provide a mathematical explanation. We use the two-phase Potts model for image segmentation as an example for our explanations. We associate the segmentation problem with a control problem in the continuous setting. Then, multigrid method and operator splitting scheme, the PottsMGNet, are used to discretize the continuous control model. We show that the resulting discrete PottsMGNet is equivalent to an encoder-decoder-based network. With minor modifications, it is shown that a number of the popular encoder-decoder-based neural networks are just instances of the proposed PottsMGNet. By incorporating the Soft-Threshold-Dynamics into the PottsMGNet as a regularizer, the PottsMGNet has shown to be robust with the network parameters such as network width and depth and achieved remarkable performance on datasets with very large noise. In nearly all our experiments, the new network always performs better or as good on accuracy and dice score than existing networks for image segmentation.
Policies often fail due to distribution shift -- changes in the state and reward that occur when a policy is deployed in new environments. Data augmentation can increase robustness by making the model invariant to task-irrelevant changes in the agent's observation. However, designers don't know which concepts are irrelevant a priori, especially when different end users have different preferences about how the task is performed. We propose an interactive framework to leverage feedback directly from the user to identify personalized task-irrelevant concepts. Our key idea is to generate counterfactual demonstrations that allow users to quickly identify possible task-relevant and irrelevant concepts. The knowledge of task-irrelevant concepts is then used to perform data augmentation and thus obtain a policy adapted to personalized user objectives. We present experiments validating our framework on discrete and continuous control tasks with real human users. Our method (1) enables users to better understand agent failure, (2) reduces the number of demonstrations required for fine-tuning, and (3) aligns the agent to individual user task preferences.
Offline Reinforcement Learning (RL) methods leverage previous experiences to learn better policies than the behavior policy used for data collection. However, they face challenges handling distribution shifts due to the lack of online interaction during training. To this end, we propose a novel method named State Reconstruction for Diffusion Policies (SRDP) that incorporates state reconstruction feature learning in the recent class of diffusion policies to address the problem of out-of-distribution (OOD) generalization. Our method promotes learning of generalizable state representation to alleviate the distribution shift caused by OOD states. To illustrate the OOD generalization and faster convergence of SRDP, we design a novel 2D Multimodal Contextual Bandit environment and realize it on a 6-DoF real-world UR10 robot, as well as in simulation, and compare its performance with prior algorithms. In particular, we show the importance of the proposed state reconstruction via ablation studies. In addition, we assess the performance of our model on standard continuous control benchmarks (D4RL), namely the navigation of an 8-DoF ant and forward locomotion of half-cheetah, hopper, and walker2d, achieving state-of-the-art results. Finally, we demonstrate that our method can achieve 167% improvement over the competing baseline on a sparse continuous control navigation task where various regions of the state space are removed from the offline RL dataset, including the region encapsulating the goal.
Learning effective continuous control policies in high-dimensional systems, including musculoskeletal agents, remains a significant challenge. Over the course of biological evolution, organisms have developed robust mechanisms for overcoming this complexity to learn highly sophisticated strategies for motor control. What accounts for this robust behavioral flexibility? Modular control via muscle synergies, i.e. coordinated muscle co-contractions, is considered to be one putative mechanism that enables organisms to learn muscle control in a simplified and generalizable action space. Drawing inspiration from this evolved motor control strategy, we use physiologically accurate human hand and leg models as a testbed for determining the extent to which a Synergistic Action Representation (SAR) acquired from simpler tasks facilitates learning more complex tasks. We find in both cases that SAR-exploiting policies significantly outperform end-to-end reinforcement learning. Policies trained with SAR were able to achieve robust locomotion on a wide set of terrains with high sample efficiency, while baseline approaches failed to learn meaningful behaviors. Additionally, policies trained with SAR on a multiobject manipulation task significantly outperformed (>70% success) baseline approaches (<20% success). Both of these SAR-exploiting policies were also found to generalize zero-shot to out-of-domain environmental conditions, while policies that did not adopt SAR failed to generalize. Finally, we establish the generality of SAR on broader high-dimensional control problems using a robotic manipulation task set and a full-body humanoid locomotion task. To the best of our knowledge, this investigation is the first of its kind to present an end-to-end pipeline for discovering synergies and using this representation to learn high-dimensional continuous control across a wide diversity of tasks.