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.
We focus on the problem of imitation learning from visual observations, where the learning agent has access to videos of experts as its sole learning source. The challenges of this framework include the absence of expert actions and the partial observability of the environment, as the ground-truth states can only be inferred from pixels. To tackle this problem, we first conduct a theoretical analysis of imitation learning in partially observable environments. We establish upper bounds on the suboptimality of the learning agent with respect to the divergence between the expert and the agent latent state-transition distributions. Motivated by this analysis, we introduce an algorithm called Latent Adversarial Imitation from Observations, which combines off-policy adversarial imitation techniques with a learned latent representation of the agent's state from sequences of observations. In experiments on high-dimensional continuous robotic tasks, we show that our algorithm matches state-of-the-art performance while providing significant computational advantages. Additionally, we show how our method can be used to improve the efficiency of reinforcement learning from pixels by leveraging expert videos. To ensure reproducibility, we provide free access to our code.
Robustness and safety are critical for the trustworthy deployment of deep reinforcement learning in real-world decision making applications. In particular, we require algorithms that can guarantee robust, safe performance in the presence of general environment disturbances, while making limited assumptions on the data collection process during training. In this work, we propose a safe reinforcement learning framework with robustness guarantees through the use of an optimal transport cost uncertainty set. We provide an efficient, theoretically supported implementation based on Optimal Transport Perturbations, which can be applied in a completely offline fashion using only data collected in a nominal training environment. We demonstrate the robust, safe performance of our approach on a variety of continuous control tasks with safety constraints in the Real-World Reinforcement Learning Suite.
Many real-world domains require safe decision making in the presence of uncertainty. In this work, we propose a deep reinforcement learning framework for approaching this important problem. We consider a risk-averse perspective towards model uncertainty through the use of coherent distortion risk measures, and we show that our formulation is equivalent to a distributionally robust safe reinforcement learning problem with robustness guarantees on performance and safety. We propose an efficient implementation that only requires access to a single training environment, and we demonstrate that our framework produces robust, safe performance on a variety of continuous control tasks with safety constraints in the Real-World Reinforcement Learning Suite.
Real-world sequential decision making requires data-driven algorithms that provide practical guarantees on performance throughout training while also making efficient use of data. Model-free deep reinforcement learning represents a framework for such data-driven decision making, but existing algorithms typically only focus on one of these goals while sacrificing performance with respect to the other. On-policy algorithms guarantee policy improvement throughout training but suffer from high sample complexity, while off-policy algorithms make efficient use of data through sample reuse but lack theoretical guarantees. In order to balance these competing goals, we develop a class of Generalized Policy Improvement algorithms that combines the policy improvement guarantees of on-policy methods with the efficiency of theoretically supported sample reuse. We demonstrate the benefits of this new class of algorithms through extensive experimental analysis on a variety of continuous control tasks from the DeepMind Control Suite.
In real-world decision making tasks, it is critical for data-driven reinforcement learning methods to be both stable and sample efficient. On-policy methods typically generate reliable policy improvement throughout training, while off-policy methods make more efficient use of data through sample reuse. In this work, we combine the theoretically supported stability benefits of on-policy algorithms with the sample efficiency of off-policy algorithms. We develop policy improvement guarantees that are suitable for the off-policy setting, and connect these bounds to the clipping mechanism used in Proximal Policy Optimization. This motivates an off-policy version of the popular algorithm that we call Generalized Proximal Policy Optimization with Sample Reuse. We demonstrate both theoretically and empirically that our algorithm delivers improved performance by effectively balancing the competing goals of stability and sample efficiency.
In order for reinforcement learning techniques to be useful in real-world decision making processes, they must be able to produce robust performance from limited data. Deep policy optimization methods have achieved impressive results on complex tasks, but their real-world adoption remains limited because they often require significant amounts of data to succeed. When combined with small sample sizes, these methods can result in unstable learning due to their reliance on high-dimensional sample-based estimates. In this work, we develop techniques to control the uncertainty introduced by these estimates. We leverage these techniques to propose a deep policy optimization approach designed to produce stable performance even when data is scarce. The resulting algorithm, Uncertainty-Aware Trust Region Policy Optimization, generates robust policy updates that adapt to the level of uncertainty present throughout the learning process.