Current approaches to model-based offline Reinforcement Learning (RL) often incorporate uncertainty-based reward penalization to address the distributional shift problem. While these approaches have achieved some success, we argue that this penalization introduces excessive conservatism, potentially resulting in suboptimal policies through underestimation. We identify as an important cause of over-penalization the lack of a reliable uncertainty estimator capable of propagating uncertainties in the Bellman operator. The common approach to calculating the penalty term relies on sampling-based uncertainty estimation, resulting in high variance. To address this challenge, we propose a novel method termed Moment Matching Offline Model-Based Policy Optimization (MOMBO). MOMBO learns a Q-function using moment matching, which allows us to deterministically propagate uncertainties through the Q-function. We evaluate MOMBO's performance across various environments and demonstrate empirically that MOMBO is a more stable and sample-efficient approach.

In online Inverse Reinforcement Learning (IRL), the learner can collect samples about the dynamics of the environment to improve its estimate of the reward function. Since IRL suffers from identifiability issues, many theoretical works on online IRL focus on estimating the entire set of rewards that explain the demonstrations, named the feasible reward set. However, none of the algorithms available in the literature can scale to problems with large state spaces. In this paper, we focus on the online IRL problem in Linear Markov Decision Processes (MDPs). We show that the structure offered by Linear MDPs is not sufficient for efficiently estimating the feasible set when the state space is large. As a consequence, we introduce the novel framework of rewards compatibility, which generalizes the notion of feasible set, and we develop CATY-IRL, a sample efficient algorithm whose complexity is independent of the cardinality of the state space in Linear MDPs. When restricted to the tabular setting, we demonstrate that CATY-IRL is minimax optimal up to logarithmic factors. As a by-product, we show that Reward-Free Exploration (RFE) enjoys the same worst-case rate, improving over the state-of-the-art lower bound. Finally, we devise a unifying framework for IRL and RFE that may be of independent interest.

In recent years there has been a tremendous surge in the general capabilities of AI systems, mainly fuelled by training foundation models on internetscale data. Nevertheless, the creation of openended, ever self-improving AI remains elusive. In this position paper, we argue that the ingredients are now in place to achieve openendedness in AI systems with respect to a human observer. Furthermore, we claim that such open-endedness is an essential property of any artificial superhuman intelligence (ASI). We begin by providing a concrete formal definition of open-endedness through the lens of novelty and learnability. We then illustrate a path towards ASI via open-ended systems built on top of foundation models, capable of making novel, humanrelevant discoveries. We conclude by examining the safety implications of generally-capable openended AI. We expect that open-ended foundation models will prove to be an increasingly fertile and safety-critical area of research in the near future.

Although deep reinforcement learning has demonstrated impressive achievements in controlling various autonomous systems, e.g., autonomous vehicles or humanoid robots, its inherent reliance on random exploration raises safety concerns in their real-world applications. To improve system safety during the learning process, a variety of Safe Reinforcement Learning (SRL) algorithms have been proposed, which usually incorporate safety constraints within the Constrained Markov Decision Process (CMDP) framework. However, the efficacy of these SRL algorithms often relies on accurate function approximations, a task that is notably challenging to accomplish in the early learning stages due to data insufficiency. To address this problem, we introduce a Genralizable Safety enhancer (GenSafe) in this work. Leveraging model order reduction techniques, we first construct a Reduced Order Markov Decision Process (ROMDP) as a low-dimensional proxy for the original cost function in CMDP. Then, by solving ROMDP-based constraints that are reformulated from the original cost constraints, the proposed GenSafe refines the actions taken by the agent to enhance the possibility of constraint satisfaction. Essentially, GenSafe acts as an additional safety layer for SRL algorithms, offering broad compatibility across diverse SRL approaches. The performance of GenSafe is examined on multiple SRL benchmark problems. The results show that, it is not only able to improve the safety performance, especially in the early learning phases, but also to maintain the task performance at a satisfactory level.

Many classic Reinforcement Learning (RL) algorithms rely on a Bellman operator, which involves an expectation over the next states, leading to the concept of bootstrapping. To introduce a form of pessimism, we propose to replace this expectation with an expectile. In practice, this can be very simply done by replacing the $L_2$ loss with a more general expectile loss for the critic. Introducing pessimism in RL is desirable for various reasons, such as tackling the overestimation problem (for which classic solutions are double Q-learning or the twin-critic approach of TD3) or robust RL (where transitions are adversarial). We study empirically these two cases. For the overestimation problem, we show that the proposed approach, ExpectRL, provides better results than a classic twin-critic. On robust RL benchmarks, involving changes of the environment, we show that our approach is more robust than classic RL algorithms. We also introduce a variation of ExpectRL combined with domain randomization which is competitive with state-of-the-art robust RL agents. Eventually, we also extend \ExpectRL with a mechanism for choosing automatically the expectile value, that is the degree of pessimism

Inverse reinforcement learning (IRL) aims to recover the reward function of an expert agent from demonstrations of behavior. It is well-known that the IRL problem is fundamentally ill-posed, i.e., many reward functions can explain the demonstrations. For this reason, IRL has been recently reframed in terms of estimating the feasible reward set (Metelli et al., 2021), thus, postponing the selection of a single reward. However, so far, the available formulations and algorithmic solutions have been proposed and analyzed mainly for the online setting, where the learner can interact with the environment and query the expert at will. This is clearly unrealistic in most practical applications, where the availability of an offline dataset is a much more common scenario. In this paper, we introduce a novel notion of feasible reward set capturing the opportunities and limitations of the offline setting and we analyze the complexity of its estimation. This requires the introduction an original learning framework that copes with the intrinsic difficulty of the setting, for which the data coverage is not under control. Then, we propose two computationally and statistically efficient algorithms, IRLO and PIRLO, for addressing the problem. In particular, the latter adopts a specific form of pessimism to enforce the novel desirable property of inclusion monotonicity of the delivered feasible set. With this work, we aim to provide a panorama of the challenges of the offline IRL problem and how they can be fruitfully addressed.

Robot navigation has transitioned from prioritizing obstacle avoidance to adopting socially aware navigation strategies that accommodate human presence. As a result, the recognition of socially aware navigation within dynamic human-centric environments has gained prominence in the field of robotics. Although reinforcement learning technique has fostered the advancement of socially aware navigation, defining appropriate reward functions, especially in congested environments, has posed a significant challenge. These rewards, crucial in guiding robot actions, demand intricate human-crafted design due to their complex nature and inability to be automatically set. The multitude of manually designed rewards poses issues with hyperparameter redundancy, imbalance, and inadequate representation of unique object characteristics. To address these challenges, we introduce a transformable gaussian reward function (TGRF). The TGRF significantly reduces the burden of hyperparameter tuning, displays adaptability across various reward functions, and demonstrates accelerated learning rates, particularly excelling in crowded environments utilizing deep reinforcement learning (DRL). We introduce and validate TGRF through sections highlighting its conceptual background, characteristics, experiments, and real-world application, paving the way for a more effective and adaptable approach in robotics.The complete source code is available on https://github.com/JinnnK/TGRF

Off-policy actor-critic algorithms have shown promise in deep reinforcement learning for continuous control tasks. Their success largely stems from leveraging pessimistic state-action value function updates, which effectively address function approximation errors and improve performance. However, such pessimism can lead to under-exploration, constraining the agent's ability to explore/refine its policies. Conversely, optimism can counteract under-exploration, but it also carries the risk of excessive risk-taking and poor convergence if not properly balanced. Based on these insights, we introduce Utility Soft Actor-Critic (USAC), a novel framework within the actor-critic paradigm that enables independent control over the degree of pessimism/optimism for both the actor and the critic via interpretable parameters. USAC adapts its exploration strategy based on the uncertainty of critics through a utility function that allows us to balance between pessimism and optimism separately. By going beyond binary choices of optimism and pessimism, USAC represents a significant step towards achieving balance within off-policy actor-critic algorithms. Our experiments across various continuous control problems show that the degree of pessimism or optimism depends on the nature of the task. Furthermore, we demonstrate that USAC can outperform state-of-the-art algorithms for appropriately configured pessimism/optimism parameters.

In this manuscript, we consider a particle in a turbulent flow that swims towards its passive partner to maintain proximity. The particle is controlled by a Reinforcement Learning (RL) agent [1], a methodology in Artificial Intelligence (AI) for solving complex decision-making problems. Unlike other AI methods, RL involves an agent learning through interaction with its environment, balancing exploration and exploitation. Exploration involves trying new actions to gain information about the environment (turbulence), while exploitation uses accumulated knowledge to make optimal decisions. This RL decision-making is linked to the Stochastic Optimal Control (SOC) challenge, where the agent maximizes expected reward under environmental uncertainty. In this study, the reward consists of two competing terms: maintaining distance between the agent and its partner, and penalizing the effort required. Among RL strategies, Actor-Critic (AC) methods [2] combine policy-based actors with reward-based critics. The "actor" suggests actions based on current policy, and the "critic" evaluates these actions, providing feedback to update the policy and reduce learning variance.

Robotic affordances, providing information about what actions can be taken in a given situation, can aid robotic manipulation. However, learning about affordances requires expensive large annotated datasets of interactions or demonstrations. In this work, we argue that well-directed interactions with the environment can mitigate this problem and propose an information-based measure to augment the agent's objective and accelerate the affordance discovery process. We provide a theoretical justification of our approach and we empirically validate the approach both in simulation and real-world tasks. Our method, which we dub IDA, enables the efficient discovery of visual affordances for several action primitives, such as grasping, stacking objects, or opening drawers, strongly improving data efficiency in simulation, and it allows us to learn grasping affordances in a small number of interactions, on a real-world setup with a UFACTORY XArm 6 robot arm.