Ever wish you had an inefficient but somewhat legible collection of machine learning algorithms implemented exclusively in NumPy? If you don't plan to modify the source, you can also install numpy-ml as a Python package: pip3 install -u numpy_ml. The reinforcement learning agents train on environments defined in the OpenAI gym. To install these alongside numpy-ml, you can use pip3 install -u'numpy_ml[rl]'. For more details on the available models, see the project documentation.

Taught by DeepMind researchers, this series was created in collaboration with University College London (UCL) to offer students a comprehensive introduction to modern reinforcement learning. Comprising 13 lectures, the series covers the fundamentals of reinforcement learning and planning in sequential decision problems, before progressing to more advanced topics and modern deep RL algorithms. It gives students a detailed understanding of various topics, including Markov Decision Processes, sample-based learning algorithms (e.g. It also explores more advanced topics like off-policy learning, multi-step updates and eligibility traces, as well as conceptual and practical considerations in implementing deep reinforcement learning algorithms such as rainbow DQN.

To be viable for safety-critical applications, such as autonomous driving and assistive robotics, autonomous agents should adhere to safety constraints throughout the interactions with their environments. Instead of learning about safety by collecting samples, including unsafe ones, methods such as Hamilton-Jacobi (HJ) reachability compute safe sets with theoretical guarantees using models of the system dynamics. However, HJ reachability is not scalable to high-dimensional systems, and the guarantees hinge on the quality of the model. In this work, we inject HJ reachability theory into the constrained Markov decision process (CMDP) framework, as a control-theoretical approach for safety analysis via model-free updates on state-action pairs. Furthermore, we demonstrate that the HJ safety value can be learned directly on vision context, the highest-dimensional problem studied via the method to-date. We evaluate our method on several benchmark tasks, including Safety Gym and Learn-to-Race (L2R), a recently-released high-fidelity autonomous racing environment. Our approach has significantly fewer constraint violations in comparison to other constrained RL baselines, and achieve the new state-of-the-art results on the L2R benchmark task.

Multi-agent reinforcement learning often suffers from the exponentially larger action space caused by a large number of agents. In this paper, we propose a novel value decomposition framework HAVEN based on hierarchical reinforcement learning for the fully cooperative multi-agent problems. In order to address instabilities that arise from the concurrent optimization of high-level and low-level policies and another concurrent optimization of agents, we introduce the dual coordination mechanism of inter-layer strategies and inter-agent strategies. HAVEN does not require domain knowledge and pretraining at all, and can be applied to any value decomposition variants. Our method is demonstrated to achieve superior results to many baselines on StarCraft II micromanagement tasks and offers an efficient solution to multi-agent hierarchical reinforcement learning in fully cooperative scenarios.

Human intelligence has the remarkable ability to adapt to new tasks and environments quickly. Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by following provided natural language instructions. To facilitate research in this direction, we propose IGLU: Interactive Grounded Language Understanding in a Collaborative Environment. The primary goal of the competition is to approach the problem of how to build interactive agents that learn to solve a task while provided with grounded natural language instructions in a collaborative environment. Understanding the complexity of the challenge, we split it into sub-tasks to make it feasible for participants. This research challenge is naturally related, but not limited, to two fields of study that are highly relevant to the NeurIPS community: Natural Language Understanding and Generation (NLU/G) and Reinforcement Learning (RL). Therefore, the suggested challenge can bring two communities together to approach one of the important challenges in AI. Another important aspect of the challenge is the dedication to perform a human-in-the-loop evaluation as a final evaluation for the agents developed by contestants.

Cross-domain imitation learning studies how to leverage expert demonstrations of one agent to train an imitation agent with a different embodiment or morphology. Comparing trajectories and stationary distributions between the expert and imitation agents is challenging because they live on different systems that may not even have the same dimensionality. We propose Gromov-Wasserstein Imitation Learning (GWIL), a method for cross-domain imitation that uses the Gromov-Wasserstein distance to align and compare states between the different spaces of the agents. Our theory formally characterizes the scenarios where GWIL preserves optimality, revealing its possibilities and limitations. We demonstrate the effectiveness of GWIL in non-trivial continuous control domains ranging from simple rigid transformation of the expert domain to arbitrary transformation of the state-action space.

Autonomous cyber-physical systems (CPS) can improve safety and efficiency for safety-critical applications, but require rigorous testing before deployment. The complexity of these systems often precludes the use of formal verification and real-world testing can be too dangerous during development. Therefore, simulation-based techniques have been developed that treat the system under test as a black box operating in a simulated environment. Safety validation tasks include finding disturbances in the environment that cause the system to fail (falsification), finding the most-likely failure, and estimating the probability that the system fails. Motivated by the prevalence of safety-critical artificial intelligence, this work provides a survey of state-of-the-art safety validation techniques for CPS with a focus on applied algorithms and their modifications for the safety validation problem. We present and discuss algorithms in the domains of optimization, path planning, reinforcement learning, and importance sampling. Problem decomposition techniques are presented to help scale algorithms to large state spaces, which are common for CPS. A brief overview of safety-critical applications is given, including autonomous vehicles and aircraft collision avoidance systems. Finally, we present a survey of existing academic and commercially available safety validation tools.

Reliable AI agents should be mindful of the limits of their knowledge and consult humans when sensing that they do not have sufficient knowledge to make sound decisions. We formulate a hierarchical reinforcement learning framework for learning to decide when to request additional information from humans and what type of information would be helpful to request. Our framework extends partially-observed Markov decision processes (POMDPs) by allowing an agent to interact with an assistant to leverage their knowledge in accomplishing tasks. Results on a simulated human-assisted navigation problem demonstrate the effectiveness of our framework: aided with an interaction policy learned by our method, a navigation policy achieves up to a 7x improvement in task success rate compared to performing tasks only by itself. The interaction policy is also efficient: on average, only a quarter of all actions taken during a task execution are requests for information. We analyze benefits and challenges of learning with a hierarchical policy structure and suggest directions for future work.

In reinforcement learning (RL), when defining a Markov Decision Process (MDP), the environment dynamics is implicitly assumed to be stationary. This assumption of stationarity, while simplifying, can be unrealistic in many scenarios. In the continual reinforcement learning scenario, the sequence of tasks is another source of nonstationarity. In this work, we propose to examine this continual reinforcement learning setting through the block contextual MDP (BC-MDP) framework, which enables us to relax the assumption of stationarity. This framework challenges RL algorithms to handle both nonstationarity and rich observation settings and, by additionally leveraging smoothness properties, enables us to study generalization bounds for this setting. Finally, we take inspiration from adaptive control to propose a novel algorithm that addresses the challenges introduced by this more realistic BC-MDP setting, allows for zero-shot adaptation at evaluation time, and achieves strong performance on several nonstationary environments.

Humans have mental models that allow them to plan, experiment, and reason in the physical world. How should an intelligent agent go about learning such models? In this paper, we will study if models of the world learned in an open-ended physics environment, without any specific tasks, can be reused for downstream physics reasoning tasks. To this end, we build a benchmark Open-ended Physics ENvironment (OPEn) and also design several tasks to test learning representations in this environment explicitly. This setting reflects the conditions in which real agents (i.e. rolling robots) find themselves, where they may be placed in a new kind of environment and must adapt without any teacher to tell them how this environment works. This setting is challenging because it requires solving an exploration problem in addition to a model building and representation learning problem. We test several existing RL-based exploration methods on this benchmark and find that an agent using unsupervised contrastive learning for representation learning, and impact-driven learning for exploration, achieved the best results. However, all models still fall short in sample efficiency when transferring to the downstream tasks. We expect that OPEn will encourage the development of novel rolling robot agents that can build reusable mental models of the world that facilitate many tasks.