Recently, there are many efforts attempting to learn useful policies for continuous control in visual reinforcement learning (RL). In this scenario, it is important to learn a generalizable policy, as the testing environment may differ from the training environment, e.g., there exist distractors during deployment. Many practical algorithms are proposed to handle this problem. However, to the best of our knowledge, none of them provide a theoretical understanding of what affects the generalization gap and why their proposed methods work. In this paper, we bridge this issue by theoretically answering the key factors that contribute to the generalization gap when the testing environment has distractors. Our theories indicate that minimizing the representation distance between training and testing environments, which aligns with human intuition, is the most critical for the benefit of reducing the generalization gap. Our theoretical results are supported by the empirical evidence in the DMControl Generalization Benchmark (DMC-GB).
In the field of reinforcement learning (RL), representation learning is a proven tool for complex image-based tasks, but is often overlooked for environments with low-level states, such as physical control problems. This paper introduces SALE, a novel approach for learning embeddings that model the nuanced interaction between state and action, enabling effective representation learning from low-level states. We extensively study the design space of these embeddings and highlight important design considerations. We integrate SALE and an adaptation of checkpoints for RL into TD3 to form the TD7 algorithm, which significantly outperforms existing continuous control algorithms. On OpenAI gym benchmark tasks, TD7 has an average performance gain of 276.7% and 50.7% over TD3 at 300k and 5M time steps, respectively, and works in both the online and offline settings.
We propose a scheme leveraging reinforcement learning to engineer control fields for generating non-classical states. It is exemplified by the application to prepare spin-squeezed states for an open collective spin model where a linear control field is designed to govern the dynamics. The reinforcement learning agent determines the temporal sequence of control pulses, commencing from a coherent spin state in an environment characterized by dissipation and dephasing. Compared to the constant control scenario, this approach provides various control sequences maintaining collective spin squeezing and entanglement. It is observed that denser application of the control pulses enhances the performance of the outcomes. However, there is a minor enhancement in the performance by adding control actions. The proposed strategy demonstrates increased effectiveness for larger systems. Thermal excitations of the reservoir are detrimental to the control outcomes. Feasible experiments are suggested to implement this control proposal based on the comparison with the others. The extensions to continuous control problems and another quantum system are discussed. The replaceability of the reinforcement learning module is also emphasized. This research paves the way for its application in manipulating other quantum systems.
In recent years, various powerful policy gradient algorithms have been proposed in deep reinforcement learning. While all these algorithms build on the Policy Gradient Theorem, the specific design choices differ significantly across algorithms. We provide a holistic overview of on-policy policy gradient algorithms to facilitate the understanding of both their theoretical foundations and their practical implementations. In this overview, we include a detailed proof of the continuous version of the Policy Gradient Theorem, convergence results and a comprehensive discussion of practical algorithms. We compare the most prominent algorithms on continuous control environments and provide insights on the benefits of regularization. All code is available at https://github.com/Matt00n/PolicyGradientsJax.
Among various satellite actuators, magnetic torquers have been widely equipped for stabilization and attitude control of small satellites. Although magnetorquers are generally used with other actuators, such as momentum wheels, this paper explores a control method where only a magnetic actuation is available. We applied a nonlinear optimal control method, Nonlinear Model Predictive Control (NMPC), to small satellites, employing the generalized minimal residual (GMRES) method, which generates continuous control inputs. Onboard magnetic actuation systems often find it challenging to produce smooth magnetic moments as a control input; hence, we employ the Pulse Width Modulation (PWM) method, which discretizes a control input and reduces the burden on actuators. In our case, the PWM approach discretizes control torques generated by the NMPC scheme. This study's main contributions are investigating the NMPC and the GMRES method applied to small spacecraft and presenting the PWM control system's feasibility.
Goal representation affects the performance of Hierarchical Reinforcement Learning (HRL) algorithms by decomposing the complex learning problem into easier subtasks. Recent studies show that representations that preserve temporally abstract environment dynamics are successful in solving difficult problems and provide theoretical guarantees for optimality. These methods however cannot scale to tasks where environment dynamics increase in complexity i.e. the temporally abstract transition relations depend on larger number of variables. On the other hand, other efforts have tried to use spatial abstraction to mitigate the previous issues. Their limitations include scalability to high dimensional environments and dependency on prior knowledge. In this paper, we propose a novel three-layer HRL algorithm that introduces, at different levels of the hierarchy, both a spatial and a temporal goal abstraction. We provide a theoretical study of the regret bounds of the learned policies. We evaluate the approach on complex continuous control tasks, demonstrating the effectiveness of spatial and temporal abstractions learned by this approach. Find open-source code at https://github.com/cosynus-lix/STAR.
A hallmark of intelligence is the ability to exhibit a wide range of effective behaviors. Inspired by this principle, Quality-Diversity algorithms, such as MAP-Elites, are evolutionary methods designed to generate a set of diverse and high-fitness solutions. However, as a genetic algorithm, MAP-Elites relies on random mutations, which can become inefficient in high-dimensional search spaces, thus limiting its scalability to more complex domains, such as learning to control agents directly from high-dimensional inputs. To address this limitation, advanced methods like PGA-MAP-Elites and DCG-MAP-Elites have been developed, which combine actor-critic techniques from Reinforcement Learning with MAP-Elites, significantly enhancing the performance and efficiency of Quality-Diversity algorithms in complex, high-dimensional tasks. While these methods have successfully leveraged the trained critic to guide more effective mutations, the potential of the trained actor remains underutilized in improving both the quality and diversity of the evolved population. In this work, we introduce DCRL-MAP-Elites, an extension of DCG-MAP-Elites that utilizes the descriptor-conditioned actor as a generative model to produce diverse solutions, which are then injected into the offspring batch at each generation. Additionally, we present an empirical analysis of the fitness and descriptor reproducibility of the solutions discovered by each algorithm. Finally, we present a second empirical analysis shedding light on the synergies between the different variations operators and explaining the performance improvement from PGA-MAP-Elites to DCRL-MAP-Elites.
Policy gradient methods hold great potential for solving complex continuous control tasks. Still, their training efficiency can be improved by exploiting structure within the optimization problem. Recent work indicates that supervised learning can be accelerated by leveraging the fact that gradients lie in a low-dimensional and slowly-changing subspace. In this paper, we conduct a thorough evaluation of this phenomenon for two popular deep policy gradient methods on various simulated benchmark tasks. Our results demonstrate the existence of such gradient subspaces despite the continuously changing data distribution inherent to reinforcement learning. These findings reveal promising directions for future work on more efficient reinforcement learning, e.g., through improving parameter-space exploration or enabling second-order optimization.
The reward signal plays a central role in defining the desired behaviors of agents in reinforcement learning (RL). Rewards collected from realistic environments could be perturbed, corrupted, or noisy due to an adversary, sensor error, or because they come from subjective human feedback. Thus, it is important to construct agents that can learn under such rewards. Existing methodologies for this problem make strong assumptions, including that the perturbation is known in advance, clean rewards are accessible, or that the perturbation preserves the optimal policy. We study a new, more general, class of unknown perturbations, and introduce a distributional reward critic framework for estimating reward distributions and perturbations during training. Our proposed methods are compatible with any RL algorithm. Despite their increased generality, we show that they achieve comparable or better rewards than existing methods in a variety of environments, including those with clean rewards. Under the challenging and generalized perturbations we study, we win/tie the highest return in 44/48 tested settings (compared to 11/48 for the best baseline). Our results broaden and deepen our ability to perform RL in reward-perturbed environments.
We present Self-Play Preference Optimization (SPO), an algorithm for reinforcement learning from human feedback. Our approach is minimalist in that it does not require training a reward model nor unstable adversarial training and is therefore rather simple to implement. Our approach is maximalist in that it provably handles non-Markovian, intransitive, and stochastic preferences while being robust to the compounding errors that plague offline approaches to sequential prediction. To achieve the preceding qualities, we build upon the concept of a Minimax Winner (MW), a notion of preference aggregation from the social choice theory literature that frames learning from preferences as a zero-sum game between two policies. By leveraging the symmetry of this game, we prove that rather than using the traditional technique of dueling two policies to compute the MW, we can simply have a single agent play against itself while maintaining strong convergence guarantees. Practically, this corresponds to sampling multiple trajectories from a policy, asking a preference or teacher model to compare them, and then using the proportion of wins as the reward for a particular trajectory. We demonstrate that on a suite of continuous control tasks, we are able to learn significantly more efficiently than reward-model based approaches while maintaining robustness to the intransitive and stochastic preferences that frequently occur in practice when aggregating human judgments.
Mastering deep reinforcement learning (DRL) proves challenging in tasks featuring scant rewards. These limited rewards merely signify whether the task is partially or entirely accomplished, necessitating various exploration actions before the agent garners meaningful feedback. Consequently, the majority of existing DRL exploration algorithms struggle to acquire practical policies within a reasonable timeframe. To address this challenge, we introduce an approach leveraging offline demonstration trajectories for swifter and more efficient online RL in environments with sparse rewards. Our pivotal insight involves treating offline demonstration trajectories as guidance, rather than mere imitation, allowing our method to learn a policy whose distribution of state-action visitation marginally matches that of offline demonstrations. We specifically introduce a novel trajectory distance relying on maximum mean discrepancy (MMD) and cast policy optimization as a distance-constrained optimization problem. We then illustrate that this optimization problem can be streamlined into a policy-gradient algorithm, integrating rewards shaped by insights from offline demonstrations. The proposed algorithm undergoes evaluation across extensive discrete and continuous control tasks with sparse and misleading rewards. The experimental findings demonstrate the significant superiority of our proposed algorithm over baseline methods concerning diverse exploration and the acquisition of an optimal policy.
We propose WSAC (Weighted Safe Actor-Critic), a novel algorithm for Safe Offline Reinforcement Learning (RL) under functional approximation, which can robustly optimize policies to improve upon an arbitrary reference policy with limited data coverage. WSAC is designed as a two-player Stackelberg game to optimize a refined objective function. The actor optimizes the policy against two adversarially trained value critics with small importance-weighted Bellman errors, which focus on scenarios where the actor's performance is inferior to the reference policy. In theory, we demonstrate that when the actor employs a no-regret optimization oracle, WSAC achieves a number of guarantees: (i) For the first time in the safe offline RL setting, we establish that WSAC can produce a policy that outperforms any reference policy while maintaining the same level of safety, which is critical to designing a safe algorithm for offline RL. (ii) WSAC achieves the optimal statistical convergence rate of $1/\sqrt{N}$ to the reference policy, where $N$ is the size of the offline dataset. (iii) We theoretically show that WSAC guarantees a safe policy improvement across a broad range of hyperparameters that control the degree of pessimism, indicating its practical robustness. Additionally, we offer a practical version of WSAC and compare it with existing state-of-the-art safe offline RL algorithms in several continuous control environments. WSAC outperforms all baselines across a range of tasks, supporting the theoretical results.
We study interactive imitation learning, where a learner interactively queries a demonstrating expert for action annotations, aiming to learn a policy that has performance competitive with the expert, using as few annotations as possible. We focus on the general agnostic setting where the expert demonstration policy may not be contained in the policy class used by the learner. We propose a new oracle-efficient algorithm MFTPL-P (abbreviation for Mixed Follow the Perturbed Leader with Poisson perturbations) with provable finite-sample guarantees, under the assumption that the learner is given access to samples from some ``explorative'' distribution over states. Our guarantees hold for any policy class, which is considerably broader than prior state of the art. We further propose Bootstrap-Dagger, a more practical variant that does not require additional sample access. Empirically, MFTPL-P and Bootstrap-Dagger notably surpass online and offline imitation learning baselines in continuous control tasks.
The effectiveness of reinforcement learning (RL) agents in continuous control robotics tasks is mainly dependent on the design of the underlying reward function, which is highly prone to reward hacking. A misalignment between the reward function and underlying human preferences (values, social norms) can lead to catastrophic outcomes in the real world especially in the context of robotics for critical decision making. Recent methods aim to mitigate misalignment by learning reward functions from human preferences and subsequently performing policy optimization. However, these methods inadvertently introduce a distribution shift during reward learning due to ignoring the dependence of agent-generated trajectories on the reward learning objective, ultimately resulting in sub-optimal alignment. Hence, in this work, we address this challenge by advocating for the adoption of regularized reward functions that more accurately mirror the intended behaviors of the agent. We propose a novel concept of reward regularization within the robotic RLHF (RL from Human Feedback) framework, which we refer to as \emph{agent preferences}. Our approach uniquely incorporates not just human feedback in the form of preferences but also considers the preferences of the RL agent itself during the reward function learning process. This dual consideration significantly mitigates the issue of distribution shift in RLHF with a computationally tractable algorithm. We provide a theoretical justification for the proposed algorithm by formulating the robotic RLHF problem as a bilevel optimization problem and developing a computationally tractable version of the same. We demonstrate the efficiency of our algorithm {\ours} in several continuous control benchmarks in DeepMind Control Suite \cite{tassa2018deepmind}.
In reinforcement learning, the optimism in the face of uncertainty (OFU) is a mainstream principle for directing exploration towards less explored areas, characterized by higher uncertainty. However, in the presence of environmental stochasticity (noise), purely optimistic exploration may lead to excessive probing of high-noise areas, consequently impeding exploration efficiency. Hence, in exploring noisy environments, while optimism-driven exploration serves as a foundation, prudent attention to alleviating unnecessary over-exploration in high-noise areas becomes beneficial. In this work, we propose Optimistic Value Distribution Explorer (OVD-Explorer) to achieve a noise-aware optimistic exploration for continuous control. OVD-Explorer proposes a new measurement of the policy's exploration ability considering noise in optimistic perspectives, and leverages gradient ascent to drive exploration. Practically, OVD-Explorer can be easily integrated with continuous control RL algorithms. Extensive evaluations on the MuJoCo and GridChaos tasks demonstrate the superiority of OVD-Explorer in achieving noise-aware optimistic exploration.
Extensive utilization of deep reinforcement learning (DRL) policy networks in diverse continuous control tasks has raised questions regarding performance degradation in expansive state spaces where the input state norm is larger than that in the training environment. This paper aims to uncover the underlying factors contributing to such performance deterioration when dealing with expanded state spaces, using a novel analysis technique known as state division. In contrast to prior approaches that employ state division merely as a post-hoc explanatory tool, our methodology delves into the intrinsic characteristics of DRL policy networks. Specifically, we demonstrate that the expansion of state space induces the activation function $\tanh$ to exhibit saturability, resulting in the transformation of the state division boundary from nonlinear to linear. Our analysis centers on the paradigm of the double-integrator system, revealing that this gradual shift towards linearity imparts a control behavior reminiscent of bang-bang control. However, the inherent linearity of the division boundary prevents the attainment of an ideal bang-bang control, thereby introducing unavoidable overshooting. Our experimental investigations, employing diverse RL algorithms, establish that this performance phenomenon stems from inherent attributes of the DRL policy network, remaining consistent across various optimization algorithms.
Recent advances in learning techniques have garnered attention for their applicability to a diverse range of real-world sequential decision-making problems. Yet, many practical applications have critical constraints for operation in real environments. Most learning solutions often neglect the risk of failing to meet these constraints, hindering their implementation in real-world contexts. In this paper, we propose a risk-aware decision-making framework for contextual bandit problems, accommodating constraints and continuous action spaces. Our approach employs an actor multi-critic architecture, with each critic characterizing the distribution of performance and constraint metrics. Our framework is designed to cater to various risk levels, effectively balancing constraint satisfaction against performance. To demonstrate the effectiveness of our approach, we first compare it against state-of-the-art baseline methods in a synthetic environment, highlighting the impact of intrinsic environmental noise across different risk configurations. Finally, we evaluate our framework in a real-world use case involving a 5G mobile network where only our approach consistently satisfies the system constraint (a signal processing reliability target) with a small performance toll (8.5% increase in power consumption).
World models are a powerful tool for developing intelligent agents. By predicting the outcome of a sequence of actions, world models enable policies to be optimised via on-policy reinforcement learning (RL) using synthetic data, i.e. in "in imagination". Existing world models are autoregressive in that they interleave predicting the next state with sampling the next action from the policy. Prediction error inevitably compounds as the trajectory length grows. In this work, we propose a novel world modelling approach that is not autoregressive and generates entire on-policy trajectories in a single pass through a diffusion model. Our approach, Policy-Guided Trajectory Diffusion (PolyGRAD), leverages a denoising model in addition to the gradient of the action distribution of the policy to diffuse a trajectory of initially random states and actions into an on-policy synthetic trajectory. We analyse the connections between PolyGRAD, score-based generative models, and classifier-guided diffusion models. Our results demonstrate that PolyGRAD outperforms state-of-the-art baselines in terms of trajectory prediction error for short trajectories, with the exception of autoregressive diffusion. For short trajectories, PolyGRAD obtains similar errors to autoregressive diffusion, but with lower computational requirements. For long trajectories, PolyGRAD obtains comparable performance to baselines. Our experiments demonstrate that PolyGRAD enables performant policies to be trained via on-policy RL in imagination for MuJoCo continuous control domains. Thus, PolyGRAD introduces a new paradigm for accurate on-policy world modelling without autoregressive sampling.
Offline meta-reinforcement learning (meta-RL) methods, which adapt to unseen target tasks with prior experience, are essential in robot control tasks. Current methods typically utilize task contexts and skills as prior experience, where task contexts are related to the information within each task and skills represent a set of temporally extended actions for solving subtasks. However, these methods still suffer from limited performance when adapting to unseen target tasks, mainly because the learned prior experience lacks generalization, i.e., they are unable to extract effective prior experience from meta-training tasks by exploration and learning of continuous latent spaces. We propose a framework called decoupled meta-reinforcement learning (DCMRL), which (1) contrastively restricts the learning of task contexts through pulling in similar task contexts within the same task and pushing away different task contexts of different tasks, and (2) utilizes a Gaussian quantization variational autoencoder (GQ-VAE) for clustering the Gaussian distributions of the task contexts and skills respectively, and decoupling the exploration and learning processes of their spaces. These cluster centers which serve as representative and discrete distributions of task context and skill are stored in task context codebook and skill codebook, respectively. DCMRL can acquire generalizable prior experience and achieve effective adaptation to unseen target tasks during the meta-testing phase. Experiments in the navigation and robot manipulation continuous control tasks show that DCMRL is more effective than previous meta-RL methods with more generalizable prior experience.
This study evaluates the application of a discrete action space reinforcement learning method (Q-learning) to the continuous control problem of robot inverted pendulum balancing. To speed up the learning process and to overcome technical difficulties related to the direct learning on the real robotic system, the learning phase is performed in simulation environment. A mathematical model of the system dynamics is implemented, deduced by curve fitting on data acquired from the real system. The proposed approach demonstrated feasible, featuring its application on a real world robot that learned to balance an inverted pendulum. This study also reinforces and demonstrates the importance of an accurate representation of the physical world in simulation to achieve a more efficient implementation of reinforcement learning algorithms in real world, even when using a discrete action space algorithm to control a continuous action.