Despite the increasing popularity of policy gradient methods, they are yet to be widely utilized in sample-scarce applications, such as robotics. The sample efficiency could be improved by making best usage of available information. As a key component in reinforcement learning, the reward function is usually devised carefully to guide the agent. Hence, the reward function is usually known, allowing access to not only scalar reward signals but also reward gradients. To benefit from reward gradients, previous works require the knowledge of environment dynamics, which are hard to obtain. In this work, we develop the \textit{Reward Policy Gradient} estimator, a novel approach that integrates reward gradients without learning a model. Bypassing the model dynamics allows our estimator to achieve a better bias-variance trade-off, which results in a higher sample efficiency, as shown in the empirical analysis. Our method also boosts the performance of Proximal Policy Optimization on different MuJoCo control tasks.
In this paper, we study the controllability of an Expressive TTS system trained on a dataset for a continuous control. The dataset is the Blizzard 2013 dataset based on audiobooks read by a female speaker containing a great variability in styles and expressiveness. Controllability is evaluated with both an objective and a subjective experiment. The objective assessment is based on a measure of correlation between acoustic features and the dimensions of the latent space representing expressiveness. The subjective assessment is based on a perceptual experiment in which users are shown an interface for Controllable Expressive TTS and asked to retrieve a synthetic utterance whose expressiveness subjectively corresponds to that a reference utterance.
Active inference, a theoretical construct inspired by brain processing, is a promising alternative to control artificial agents. However, current methods do not yet scale to high-dimensional inputs in continuous control. Here we present a novel active inference torque controller for industrial arms that maintains the adaptive characteristics of previous proprioceptive approaches but also enables large-scale multimodal integration (e.g., raw images). We extended our previous mathematical formulation by including multimodal state representation learning using a linearly coupled multimodal variational autoencoder. We evaluated our model on a simulated 7DOF Franka Emika Panda robot arm and compared its behavior with a previous active inference baseline and the Panda built-in optimized controller. Results showed improved tracking and control in goal-directed reaching due to the increased representation power, high robustness to noise and adaptability in changes on the environmental conditions and robot parameters without the need to relearn the generative models nor parameters retuning.
World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms. While learning world models for high-dimensional observations (e.g., pixel inputs) has become practicable on standard RL benchmarks and some games, their effectiveness in real-world robotics applications has not been explored. In this paper, we investigate how such agents generalize to real-world autonomous vehicle control tasks, where advanced model-free deep RL algorithms fail. In particular, we set up a series of time-lap tasks for an F1TENTH racing robot, equipped with a high-dimensional LiDAR sensor, on a set of test tracks with a gradual increase in their complexity. In this continuous-control setting, we show that model-based agents capable of learning in imagination substantially outperform model-free agents with respect to performance, sample efficiency, successful task completion, and generalization. Moreover, we show that the generalization ability of model-based agents strongly depends on the choice of their observation model. We provide extensive empirical evidence for the effectiveness of world models provided with long enough memory horizons in sim2real tasks.
Obstacle avoidance is a fundamental and challenging problem for autonomous navigation of mobile robots. In this paper, we consider the problem of obstacle avoidance in simple 3D environments where the robot has to solely rely on a single monocular camera. In particular, we are interested in solving this problem without relying on localization, mapping, or planning techniques. Most of the existing work consider obstacle avoidance as two separate problems, namely obstacle detection, and control. Inspired by the recent advantages of deep reinforcement learning in Atari games and understanding highly complex situations in Go, we tackle the obstacle avoidance problem as a data-driven end-to-end deep learning approach. Our approach takes raw images as input and generates control commands as output. We show that discrete action spaces are outperforming continuous control commands in terms of expected average reward in maze-like environments. Furthermore, we show how to accelerate the learning and increase the robustness of the policy by incorporating predicted depth maps by a generative adversarial network.
Value function is the central notion of Reinforcement Learning (RL). Value estimation, especially with function approximation, can be challenging since it involves the stochasticity of environmental dynamics and reward signals that can be sparse and delayed in some cases. A typical model-free RL algorithm usually estimates the values of a policy by Temporal Difference (TD) or Monte Carlo (MC) algorithms directly from rewards, without explicitly taking dynamics into consideration. In this paper, we propose Value Decomposition with Future Prediction (VDFP), providing an explicit two-step understanding of the value estimation process: 1) first foresee the latent future, 2) and then evaluate it. We analytically decompose the value function into a latent future dynamics part and a policy-independent trajectory return part, inducing a way to model latent dynamics and returns separately in value estimation. Further, we derive a practical deep RL algorithm, consisting of a convolutional model to learn compact trajectory representation from past experiences, a conditional variational auto-encoder to predict the latent future dynamics and a convex return model that evaluates trajectory representation. In experiments, we empirically demonstrate the effectiveness of our approach for both off-policy and on-policy RL in several OpenAI Gym continuous control tasks as well as a few challenging variants with delayed reward.
We study feedback controller synthesis for reach-avoid control of discrete-time, linear time-invariant (LTI) systems with Gaussian process and measurement noise. The problem is to compute a controller such that, with at least some required probability, the system reaches a desired goal state in finite time while avoiding unsafe states. Due to stochasticity and nonconvexity, this problem does not admit exact algorithmic or closed-form solutions in general. Our key contribution is a correct-by-construction controller synthesis scheme based on a finite-state abstraction of a Gaussian belief over the unmeasured state, obtained using a Kalman filter. We formalize this abstraction as a Markov decision process (MDP). To be robust against numerical imprecision in approximating transition probabilities, we use MDPs with intervals of transition probabilities. By construction, any policy on the abstraction can be refined into a piecewise linear feedback controller for the LTI system. We prove that the closed-loop LTI system under this controller satisfies the reach-avoid problem with at least the required probability. The numerical experiments show that our method is able to solve reach-avoid problems for systems with up to 6D state spaces, and with control input constraints that cannot be handled by methods such as the rapidly-exploring random belief trees (RRBT).
Recent research has shown that graph neural networks (GNNs) can learn policies for locomotion control that are as effective as a typical multi-layer perceptron (MLP), with superior transfer and multi-task performance (Wang et al., 2018; Huang et al., 2020). Results have so far been limited to training on small agents, with the performance of GNNs deteriorating rapidly as the number of sensors and actuators grows. A key motivation for the use of GNNs in the supervised learning setting is their applicability to large graphs, but this benefit has not yet been realised for locomotion control. We identify the weakness with a common GNN architecture that causes this poor scaling: overfitting in the MLPs within the network that encode, decode, and propagate messages. To combat this, we introduce Snowflake, a GNN training method for high-dimensional continuous control that freezes parameters in parts of the network that suffer from overfitting. Snowflake significantly boosts the performance of GNNs for locomotion control on large agents, now matching the performance of MLPs, and with superior transfer properties.
Off-policy multi-step reinforcement learning algorithms consist of conservative and non-conservative algorithms: the former actively cut traces, whereas the latter do not. Recently, Munos et al. (2016) proved the convergence of conservative algorithms to an optimal Q-function. In contrast, non-conservative algorithms are thought to be unsafe and have a limited or no theoretical guarantee. Nonetheless, recent studies have shown that non-conservative algorithms empirically outperform conservative ones. Motivated by the empirical results and the lack of theory, we carry out theoretical analyses of Peng's Q($\lambda$), a representative example of non-conservative algorithms. We prove that it also converges to an optimal policy provided that the behavior policy slowly tracks a greedy policy in a way similar to conservative policy iteration. Such a result has been conjectured to be true but has not been proven. We also experiment with Peng's Q($\lambda$) in complex continuous control tasks, confirming that Peng's Q($\lambda$) often outperforms conservative algorithms despite its simplicity. These results indicate that Peng's Q($\lambda$), which was thought to be unsafe, is a theoretically-sound and practically effective algorithm.
Low-precision training has become a popular approach to reduce compute requirements, memory footprint, and energy consumption in supervised learning. In contrast, this promising approach has not yet enjoyed similarly widespread adoption within the reinforcement learning (RL) community, partly because RL agents can be notoriously hard to train even in full precision. In this paper we consider continuous control with the state-of-the-art SAC agent and demonstrate that a na\"ive adaptation of low-precision methods from supervised learning fails. We propose a set of six modifications, all straightforward to implement, that leaves the underlying agent and its hyperparameters unchanged but improves the numerical stability dramatically. The resulting modified SAC agent has lower memory and compute requirements while matching full-precision rewards, demonstrating that low-precision training can substantially accelerate state-of-the-art RL without parameter tuning.
Control of batch processes is a difficult task due to their complex nonlinear dynamics and unsteady-state operating conditions within batch and batch-to-batch. It is expected that some of these challenges can be addressed by developing control strategies that directly interact with the process and learning from experiences. Recent studies in the literature have indicated the advantage of having an ensemble of actors in actor-critic Reinforcement Learning (RL) frameworks for improving the policy. The present study proposes an actor-critic RL algorithm, namely, twin actor twin delayed deep deterministic policy gradient (TATD3), by incorporating twin actor networks in the existing twin-delayed deep deterministic policy gradient (TD3) algorithm for the continuous control. In addition, two types of novel reward functions are also proposed for TATD3 controller. We showcase the efficacy of the TATD3 based controller for various batch process examples by comparing it with some of the existing RL algorithms presented in the literature.
Approaches for teaching learning agents via human demonstrations have been widely studied and successfully applied to multiple domains. However, the majority of imitation learning work utilizes only behavioral information from the demonstrator, i.e. which actions were taken, and ignores other useful information. In particular, eye gaze information can give valuable insight towards where the demonstrator is allocating visual attention, and holds the potential to improve agent performance and generalization. In this work, we propose Gaze Regularized Imitation Learning (GRIL), a novel context-aware, imitation learning architecture that learns concurrently from both human demonstrations and eye gaze to solve tasks where visual attention provides important context. We apply GRIL to a visual navigation task, in which an unmanned quadrotor is trained to search for and navigate to a target vehicle in a photorealistic simulated environment. We show that GRIL outperforms several state-of-the-art gaze-based imitation learning algorithms, simultaneously learns to predict human visual attention, and generalizes to scenarios not present in the training data. Supplemental videos and code can be found at https://sites.google.com/view/gaze-regularized-il/.
Model-based offline reinforcement learning approaches generally rely on bounds of model error. Estimating these bounds is usually achieved through uncertainty estimation methods. In this work, we combine parametric and nonparametric methods for uncertainty estimation through a novel latent space based metric. In particular, we build upon recent advances in Riemannian geometry of generative models to construct a pullback metric of an encoder-decoder based forward model. Our proposed metric measures both the quality of out-of-distribution samples as well as the discrepancy of examples in the data. We leverage our method for uncertainty estimation in a pessimistic model-based framework, showing a significant improvement upon contemporary model-based offline approaches on continuous control and autonomous driving benchmarks.
Optimizing the combustion efficiency of a thermal power generating unit (TPGU) is a highly challenging and critical task in the energy industry. We develop a new data-driven AI system, namely DeepThermal, to optimize the combustion control strategy for TPGUs. At its core, is a new model-based offline reinforcement learning (RL) framework, called MORE, which leverages historical operational data of a TGPU to solve a highly complex constrained Markov decision process problem via purely offline training. In DeepThermal, we first learn a data-driven combustion process simulator from the offline dataset. The RL agent of MORE is then trained by combining real historical data as well as carefully filtered and processed simulation data through a novel restrictive exploration scheme. DeepThermal has been successfully deployed in four large coal-fired thermal power plants in China. Real-world experiments show that DeepThermal effectively improves the combustion efficiency of TPGUs. We also report the superior performance of MORE by comparing with the state-of-the-art algorithms on the standard offline RL benchmarks.
Modern policy gradient algorithms such as Proximal Policy Optimization (PPO) rely on an arsenal of heuristics, including loss clipping and gradient clipping, to ensure successful learning. These heuristics are reminiscent of techniques from robust statistics, commonly used for estimation in outlier-rich (``heavy-tailed'') regimes. In this paper, we present a detailed empirical study to characterize the heavy-tailed nature of the gradients of the PPO surrogate reward function. We demonstrate that the gradients, especially for the actor network, exhibit pronounced heavy-tailedness and that it increases as the agent's policy diverges from the behavioral policy (i.e., as the agent goes further off policy). Further examination implicates the likelihood ratios and advantages in the surrogate reward as the main sources of the observed heavy-tailedness. We then highlight issues arising due to the heavy-tailed nature of the gradients. In this light, we study the effects of the standard PPO clipping heuristics, demonstrating that these tricks primarily serve to offset heavy-tailedness in gradients. Thus motivated, we propose incorporating GMOM, a high-dimensional robust estimator, into PPO as a substitute for three clipping tricks. Despite requiring less hyperparameter tuning, our method matches the performance of PPO (with all heuristics enabled) on a battery of MuJoCo continuous control tasks.
Learning effective representations in image-based environments is crucial for sample efficient Reinforcement Learning (RL). Unfortunately, in RL, representation learning is confounded with the exploratory experience of the agent -- learning a useful representation requires diverse data, while effective exploration is only possible with coherent representations. Furthermore, we would like to learn representations that not only generalize across tasks but also accelerate downstream exploration for efficient task-specific training. To address these challenges we propose Proto-RL, a self-supervised framework that ties representation learning with exploration through prototypical representations. These prototypes simultaneously serve as a summarization of the exploratory experience of an agent as well as a basis for representing observations. We pre-train these task-agnostic representations and prototypes on environments without downstream task information. This enables state-of-the-art downstream policy learning on a set of difficult continuous control tasks.
Accuracy and generalization of dynamics models is key to the success of model-based reinforcement learning (MBRL). As the complexity of tasks increases, so does the sample inefficiency of learning accurate dynamics models. However, many complex tasks also exhibit sparsity in the dynamics, i.e., actions have only a local effect on the system dynamics. In this paper, we exploit this property with a causal invariance perspective in the single-task setting, introducing a new type of state abstraction called \textit{model-invariance}. Unlike previous forms of state abstractions, a model-invariance state abstraction leverages causal sparsity over state variables. This allows for compositional generalization to unseen states, something that non-factored forms of state abstractions cannot do. We prove that an optimal policy can be learned over this model-invariance state abstraction and show improved generalization in a simple toy domain. Next, we propose a practical method to approximately learn a model-invariant representation for complex domains and validate our approach by showing improved modelling performance over standard maximum likelihood approaches on challenging tasks, such as the MuJoCo-based Humanoid. Finally, within the MBRL setting we show strong performance gains with respect to sample efficiency across a host of other continuous control tasks.
Efficient exploration has presented a long-standing challenge in reinforcement learning, especially when rewards are sparse. A developmental system can overcome this difficulty by learning from both demonstrations and self-exploration. However, existing methods are not applicable to most real-world robotic controlling problems because they assume that environments follow Markov decision processes (MDP); thus, they do not extend to partially observable environments where historical observations are necessary for decision making. This paper builds on the idea of replaying demonstrations for memory-dependent continuous control, by proposing a novel algorithm, Recurrent Actor-Critic with Demonstration and Experience Replay (READER). Experiments involving several memory-crucial continuous control tasks reveal significantly reduce interactions with the environment using our method with a reasonably small number of demonstration samples. The algorithm also shows better sample efficiency and learning capabilities than a baseline reinforcement learning algorithm for memory-based control from demonstrations.
We study the following question in the context of imitation learning for continuous control: how are the underlying stability properties of an expert policy reflected in the sample-complexity of an imitation learning task? We provide the first results showing that a surprisingly granular connection can be made between the underlying expert system's incremental gain stability, a novel measure of robust convergence between pairs of system trajectories, and the dependency on the task horizon $T$ of the resulting generalization bounds. In particular, we propose and analyze incremental gain stability constrained versions of behavior cloning and a DAgger-like algorithm, and show that the resulting sample-complexity bounds naturally reflect the underlying stability properties of the expert system. As a special case, we delineate a class of systems for which the number of trajectories needed to achieve $\varepsilon$-suboptimality is sublinear in the task horizon $T$, and do so without requiring (strong) convexity of the loss function in the policy parameters. Finally, we conduct numerical experiments demonstrating the validity of our insights on both a simple nonlinear system for which the underlying stability properties can be easily tuned, and on a high-dimensional quadrupedal robotic simulation.
Sample efficiency and performance in the offline setting have emerged as significant challenges of deep reinforcement learning. We introduce Q-Value Weighted Regression (QWR), a simple RL algorithm that excels in these aspects. QWR is an extension of Advantage Weighted Regression (AWR), an off-policy actor-critic algorithm that performs very well on continuous control tasks, also in the offline setting, but has low sample efficiency and struggles with high-dimensional observation spaces. We perform an analysis of AWR that explains its shortcomings and use these insights to motivate QWR. We show experimentally that QWR matches the state-of-the-art algorithms both on tasks with continuous and discrete actions. In particular, QWR yields results on par with SAC on the MuJoCo suite and - with the same set of hyperparameters - yields results on par with a highly tuned Rainbow implementation on a set of Atari games. We also verify that QWR performs well in the offline RL setting.