** Inverse reinforcement learning is a paradigm motivated by the goal of learning general reward functions from demonstrated behaviours. Yet the notion of generality for learnt costs is often evaluated in terms of robustness to various spatial perturbations only, assuming deployment at fixed speeds of execution. However, this is impractical in the context of robotics and building, time-invariant solutions is of crucial importance. In this work, we propose a formulation that allows us to 1) vary the length of execution by learning time-invariant costs, and 2) relax the temporal alignment requirements for learning from demonstration. We apply our method to two different types of cost formulations and evaluate their performance in the context of learning reward functions for simulated placement and peg in hole tasks executed on a 7DoF Kuka IIWA arm. Our results show that our approach enables learning temporally invariant rewards from misaligned demonstration that can also generalise spatially to out of distribution tasks. **

强化学习（RL）是机器学习的一个领域，与软件代理应如何在环境中采取行动以最大化累积奖励的概念有关。除了监督学习和非监督学习外，强化学习是三种基本的机器学习范式之一。
强化学习与监督学习的不同之处在于，不需要呈现带标签的输入/输出对，也不需要显式纠正次优动作。相反，重点是在探索（未知领域）和利用（当前知识）之间找到平衡。
该环境通常以马尔可夫决策过程（MDP）的形式陈述，因为针对这种情况的许多强化学习算法都使用动态编程技术。经典动态规划方法和强化学习算法之间的主要区别在于，后者不假设MDP的确切数学模型，并且针对无法采用精确方法的大型MDP。

** Model-free reinforcement learning (RL) is capable of learning control policies for high-dimensional, complex robotic tasks, but tends to be data-inefficient. Model-based RL tends to be more data-efficient but often suffers from learning a high-dimensional model that is good enough for policy improvement. This limits its use to learning simple models for restrictive domains. Optimal control generates solutions without collecting any data, assuming an accurate model of the system and environment is known, which is often true in many control theory applications. However, optimal control cannot be scaled to problems with a high-dimensional state space. In this paper, we propose a novel approach to alleviate data inefficiency of model-free RL in high-dimensional problems by warm-starting the learning process using a lower-dimensional model-based solution. Particularly, we initialize a baseline function for the high-dimensional RL problem via supervision from a lower-dimensional value function, which can be obtained by solving a lower-dimensional problem with a known, approximate model using "classical" techniques such as value iteration or optimal control. Therefore, our approach implicitly exploits the model priors from simplified problem space to facilitate the policy learning in high-dimensional RL tasks. We demonstrate our approach on two representative robotic learning tasks and observe significant improvement in policy performance and learning efficiency. We also evaluate our method empirically with a third task. **

** We investigate the visual cross-embodiment imitation setting, in which agents learn policies from videos of other agents (such as humans) demonstrating the same task, but with stark differences in their embodiments -- shape, actions, end-effector dynamics, etc. In this work, we demonstrate that it is possible to automatically discover and learn vision-based reward functions from cross-embodiment demonstration videos that are robust to these differences. Specifically, we present a self-supervised method for Cross-embodiment Inverse Reinforcement Learning (XIRL) that leverages temporal cycle-consistency constraints to learn deep visual embeddings that capture task progression from offline videos of demonstrations across multiple expert agents, each performing the same task differently due to embodiment differences. Prior to our work, producing rewards from self-supervised embeddings typically required alignment with a reference trajectory, which may be difficult to acquire under stark embodiment differences. We show empirically that if the embeddings are aware of task progress, simply taking the negative distance between the current state and goal state in the learned embedding space is useful as a reward for training policies with reinforcement learning. We find our learned reward function not only works for embodiments seen during training, but also generalizes to entirely new embodiments. Additionally, when transferring real-world human demonstrations to a simulated robot, we find that XIRL is more sample efficient than current best methods. Qualitative results, code, and datasets are available at https://x-irl.github.io **

** Designing missiles' autopilot controllers has been a complex task, given the extensive flight envelope and the nonlinear flight dynamics. A solution that can excel both in nominal performance and in robustness to uncertainties is still to be found. While Control Theory often debouches into parameters' scheduling procedures, Reinforcement Learning has presented interesting results in ever more complex tasks, going from videogames to robotic tasks with continuous action domains. However, it still lacks clearer insights on how to find adequate reward functions and exploration strategies. To the best of our knowledge, this work is pioneer in proposing Reinforcement Learning as a framework for flight control. In fact, it aims at training a model-free agent that can control the longitudinal flight of a missile, achieving optimal performance and robustness to uncertainties. To that end, under TRPO's methodology, the collected experience is augmented according to HER, stored in a replay buffer and sampled according to its significance. Not only does this work enhance the concept of prioritized experience replay into BPER, but it also reformulates HER, activating them both only when the training progress converges to suboptimal policies, in what is proposed as the SER methodology. Besides, the Reward Engineering process is carefully detailed. The results show that it is possible both to achieve the optimal performance and to improve the agent's robustness to uncertainties (with low damage on nominal performance) by further training it in non-nominal environments, therefore validating the proposed approach and encouraging future research in this field. **

** The difficulty in specifying rewards for many real-world problems has led to an increased focus on learning rewards from human feedback, such as demonstrations. However, there are often many different reward functions that explain the human feedback, leaving agents with uncertainty over what the true reward function is. While most policy optimization approaches handle this uncertainty by optimizing for expected performance, many applications demand risk-averse behavior. We derive a novel policy gradient-style robust optimization approach, PG-BROIL, that optimizes a soft-robust objective that balances expected performance and risk. To the best of our knowledge, PG-BROIL is the first policy optimization algorithm robust to a distribution of reward hypotheses which can scale to continuous MDPs. Results suggest that PG-BROIL can produce a family of behaviors ranging from risk-neutral to risk-averse and outperforms state-of-the-art imitation learning algorithms when learning from ambiguous demonstrations by hedging against uncertainty, rather than seeking to uniquely identify the demonstrator's reward function. **

** In real world settings, numerous constraints are present which are hard to specify mathematically. However, for the real world deployment of reinforcement learning (RL), it is critical that RL agents are aware of these constraints, so that they can act safely. In this work, we consider the problem of learning constraints from demonstrations of a constraint-abiding agent's behavior. We experimentally validate our approach and show that our framework can successfully learn the most likely constraints that the agent respects. We further show that these learned constraints are \textit{transferable} to new agents that may have different morphologies and/or reward functions. Previous works in this regard have either mainly been restricted to tabular (discrete) settings, specific types of constraints or assume the environment's transition dynamics. In contrast, our framework is able to learn arbitrary \textit{Markovian} constraints in high-dimensions in a completely model-free setting. The code can be found it: \url{https://github.com/shehryar-malik/icrl}. **

** Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution shift. When the test task distribution is different from the training task distribution, the performance may degrade significantly. To address this issue, this paper proposes Model-based Adversarial Meta-Reinforcement Learning (AdMRL), where we aim to minimize the worst-case sub-optimality gap -- the difference between the optimal return and the return that the algorithm achieves after adaptation -- across all tasks in a family of tasks, with a model-based approach. We propose a minimax objective and optimize it by alternating between learning the dynamics model on a fixed task and finding the adversarial task for the current model -- the task for which the policy induced by the model is maximally suboptimal. Assuming the family of tasks is parameterized, we derive a formula for the gradient of the suboptimality with respect to the task parameters via the implicit function theorem, and show how the gradient estimator can be efficiently implemented by the conjugate gradient method and a novel use of the REINFORCE estimator. We evaluate our approach on several continuous control benchmarks and demonstrate its efficacy in the worst-case performance over all tasks, the generalization power to out-of-distribution tasks, and in training and test time sample efficiency, over existing state-of-the-art meta-RL algorithms. **

** Active learning from demonstration allows a robot to query a human for specific types of input to achieve efficient learning. Existing work has explored a variety of active query strategies; however, to our knowledge, none of these strategies directly minimize the performance risk of the policy the robot is learning. Utilizing recent advances in performance bounds for inverse reinforcement learning, we propose a risk-aware active inverse reinforcement learning algorithm that focuses active queries on areas of the state space with the potential for large generalization error. We show that risk-aware active learning outperforms standard active IRL approaches on gridworld, simulated driving, and table setting tasks, while also providing a performance-based stopping criterion that allows a robot to know when it has received enough demonstrations to safely perform a task. **

** Deep reinforcement learning suggests the promise of fully automated learning of robotic control policies that directly map sensory inputs to low-level actions. However, applying deep reinforcement learning methods on real-world robots is exceptionally difficult, due both to the sample complexity and, just as importantly, the sensitivity of such methods to hyperparameters. While hyperparameter tuning can be performed in parallel in simulated domains, it is usually impractical to tune hyperparameters directly on real-world robotic platforms, especially legged platforms like quadrupedal robots that can be damaged through extensive trial-and-error learning. In this paper, we develop a stable variant of the soft actor-critic deep reinforcement learning algorithm that requires minimal hyperparameter tuning, while also requiring only a modest number of trials to learn multilayer neural network policies. This algorithm is based on the framework of maximum entropy reinforcement learning, and automatically trades off exploration against exploitation by dynamically and automatically tuning a temperature parameter that determines the stochasticity of the policy. We show that this method achieves state-of-the-art performance on four standard benchmark environments. We then demonstrate that it can be used to learn quadrupedal locomotion gaits on a real-world Minitaur robot, learning to walk from scratch directly in the real world in two hours of training. **

** Meta-learning is a powerful tool that builds on multi-task learning to learn how to quickly adapt a model to new tasks. In the context of reinforcement learning, meta-learning algorithms can acquire reinforcement learning procedures to solve new problems more efficiently by meta-learning prior tasks. The performance of meta-learning algorithms critically depends on the tasks available for meta-training: in the same way that supervised learning algorithms generalize best to test points drawn from the same distribution as the training points, meta-learning methods generalize best to tasks from the same distribution as the meta-training tasks. In effect, meta-reinforcement learning offloads the design burden from algorithm design to task design. If we can automate the process of task design as well, we can devise a meta-learning algorithm that is truly automated. In this work, we take a step in this direction, proposing a family of unsupervised meta-learning algorithms for reinforcement learning. We describe a general recipe for unsupervised meta-reinforcement learning, and describe an effective instantiation of this approach based on a recently proposed unsupervised exploration technique and model-agnostic meta-learning. We also discuss practical and conceptual considerations for developing unsupervised meta-learning methods. Our experimental results demonstrate that unsupervised meta-reinforcement learning effectively acquires accelerated reinforcement learning procedures without the need for manual task design, significantly exceeds the performance of learning from scratch, and even matches performance of meta-learning methods that use hand-specified task distributions. **