Agent decision making using Reinforcement Learning (RL) heavily relies on either a model or simulator of the environment (e.g., moving in an 8x8 maze with three rooms, playing Chess on an 8x8 board). Due to this dependence, small changes in the environment (e.g., positions of obstacles in the maze, size of the board) can severely affect the effectiveness of the policy learned by the agent. To that end, existing work has proposed training RL agents on an adaptive curriculum of environments (generated automatically) to improve performance on out-of-distribution (OOD) test scenarios. Specifically, existing research has employed the potential for the agent to learn in an environment (captured using Generalized Advantage Estimation, GAE) as the key factor to select the next environment(s) to train the agent. However, such a mechanism can select similar environments (with a high potential to learn) thereby making agent training redundant on all but one of those environments. To that end, we provide a principled approach to adaptively identify diverse environments based on a novel distance measure relevant to environment design. We empirically demonstrate the versatility and effectiveness of our method in comparison to multiple leading approaches for unsupervised environment design on three distinct benchmark problems used in literature.

Deep Reinforcement Learning (DRL) policies have been shown to be vulnerable to small adversarial noise in observations. Such adversarial noise can have disastrous consequences in safety-critical environments. For instance, a self-driving car receiving adversarially perturbed sensory observations about nearby signs (e.g., a stop sign physically altered to be perceived as a speed limit sign) or objects (e.g., cars altered to be recognized as trees) can be fatal. Existing approaches for making RL algorithms robust to an observation-perturbing adversary have focused on reactive approaches that iteratively improve against adversarial examples generated at each iteration. While such approaches have been shown to provide improvements over regular RL methods, they are reactive and can fare significantly worse if certain categories of adversarial examples are not generated during training. To that end, we pursue a more proactive approach that relies on directly optimizing a well-studied robustness measure, regret instead of expected value. We provide a principled approach that minimizes maximum regret over a "neighborhood" of observations to the received "observation". Our regret criterion can be used to modify existing value- and policy-based Deep RL methods. We demonstrate that our approaches provide a significant improvement in performance across a wide variety of benchmarks against leading approaches for robust Deep RL.

Recent work on designing an appropriate distribution of environments has shown promise for training effective generally capable agents. Its success is partly because of a form of adaptive curriculum learning that generates environment instances (or levels) at the frontier of the agent's capabilities. However, such an environment design framework often struggles to find effective levels in challenging design spaces and requires costly interactions with the environment. In this paper, we aim to introduce diversity in the Unsupervised Environment Design (UED) framework. Specifically, we propose a task-agnostic method to identify observed/hidden states that are representative of a given level. The outcome of this method is then utilized to characterize the diversity between two levels, which as we show can be crucial to effective performance. In addition, to improve sampling efficiency, we incorporate the self-play technique that allows the environment generator to automatically generate environments that are of great benefit to the training agent. Quantitatively, our approach, Diversity-induced Environment Design via Self-Play (MBeDED), shows compelling performance over existing methods.

Advancements in reinforcement learning (RL) have demonstrated superhuman performance in complex tasks such as Starcraft, Go, Chess etc. However, knowledge transfer from Artificial "Experts" to humans remain a significant challenge. A promising avenue for such transfer would be the use of curricula. Recent methods in curricula generation focuses on training RL agents efficiently, yet such methods rely on surrogate measures to track student progress, and are not suited for training robots in the real world (or more ambitiously humans). In this paper, we introduce a method named Parameterized Environment Response Model (PERM) that shows promising results in training RL agents in parameterized environments. Inspired by Item Response Theory, PERM seeks to model difficulty of environments and ability of RL agents directly. Given that RL agents and humans are trained more efficiently under the "zone of proximal development", our method generates a curriculum by matching the difficulty of an environment to the current ability of the student. In addition, PERM can be trained offline and does not employ non-stationary measures of student ability, making it suitable for transfer between students. We demonstrate PERM's ability to represent the environment parameter space, and training with RL agents with PERM produces a strong performance in deterministic environments. Lastly, we show that our method is transferable between students, without any sacrifice in training quality.

Constrained Reinforcement Learning has been employed to compute safe policies through the use of expected cost constraints. The key challenge is in handling constraints on expected cost accumulated across time steps. Existing methods have developed innovative ways of converting this cost constraint over entire policy to constraints over local decisions (at each time step). While such approaches have provided good solutions with regards to objective, they can either be overly aggressive or conservative with respect to costs. This is owing to use of estimates for "future" or "backward" costs in local cost constraints. To that end, we provide an equivalent unconstrained formulation to constrained RL that has an augmented state space and reward penalties. This intuitive formulation is general and has interesting theoretical properties. More importantly, this provides a new paradigm for solving richly constrained (e.g., constraints on expected cost, Value at Risk, Conditional Value at Risk) Reinforcement Learning problems effectively. As we show in our experimental results, we are able to outperform leading approaches for different constraint types on multiple benchmark problems.

In large-scale multi-agent systems like taxi fleets, individual agents (taxi drivers) are self-interested (maximizing their own profits) and this can introduce inefficiencies in the system. One such inefficiency is with regard to the "required" availability of taxis at different time periods during the day. Since a taxi driver can work for a limited number of hours in a day (e.g., 8-10 hours in a city like Singapore), there is a need to optimize the specific hours, so as to maximize individual as well as social welfare. Technically, this corresponds to solving a large-scale multi-stage selfish routing game with transition uncertainty. Existing work in addressing this problem is either unable to handle ``driver" constraints (e.g., breaks during work hours) or not scalable. To that end, we provide a novel mechanism that builds on replicator dynamics through ideas from behavior cloning. We demonstrate that our methods provide significantly better policies than the existing approach in terms of improving individual agent revenue and overall agent availability.

Safety in goal directed Reinforcement Learning (RL) settings has typically been handled through constraints over trajectories and have demonstrated good performance in primarily short horizon tasks (goal is not too far away). In this paper, we are specifically interested in the problem of solving temporally extended decision making problems such as (1) robots that have to clean different areas in a house while avoiding slippery and unsafe areas (e.g., stairs) and retaining enough charge to move to a charging dock; (2) autonomous electric vehicles that have to reach a far away destination while having to optimize charging locations along the way; in the presence of complex safety constraints. Our key contribution is a (safety) Constrained Planning with Reinforcement Learning (CoP-RL) mechanism that combines a high-level constrained planning agent (which computes a reward maximizing path from a given start to a far away goal state while satisfying cost constraints) with a low-level goal conditioned RL agent (which estimates cost and reward values to move between nearby states). A major advantage of CoP-RL is that it can handle constraints on the cost value distribution (e.g., on Conditional Value at Risk, CVaR, and also on expected value). We perform extensive experiments with different types of safety constraints to demonstrate the utility of our approach over leading best approaches in constrained and hierarchical RL.

In multi-agent systems with large number of agents, typically the contribution of each agent to the value of other agents is minimal (e.g., aggregation systems such as Uber, Deliveroo). In this paper, we consider such multi-agent systems where each agent is self-interested and takes a sequence of decisions and represent them as a Stochastic Non-atomic Congestion Game (SNCG). We derive key properties for equilibrium solutions in SNCG model with non-atomic and also nearly non-atomic agents. With those key equilibrium properties, we provide a novel Multi-Agent Reinforcement Learning (MARL) mechanism that minimizes variance across values of agents in the same state. To demonstrate the utility of this new mechanism, we provide detailed results on a real-world taxi dataset and also a generic simulator for aggregation systems. We show that our approach reduces the variance in revenues earned by taxi drivers, while still providing higher joint revenues than leading approaches.

Restless multi-armed bandits (RMAB) is a framework for allocating limited resources under uncertainty. It is an extremely useful model for monitoring beneficiaries and executing timely interventions to ensure maximum benefit in public health settings (e.g., ensuring patients take medicines in tuberculosis settings, ensuring pregnant mothers listen to automated calls about good pregnancy practices). Due to the limited resources, typically certain communities or regions are starved of interventions that can have follow-on effects. To avoid starvation in the executed interventions across individuals/regions/communities, we first provide a soft fairness constraint and then provide an approach to enforce the soft fairness constraint in RMABs. The soft fairness constraint requires that an algorithm never probabilistically favor one arm over another if the long-term cumulative reward of choosing the latter arm is higher. Our approach incorporates softmax based value iteration method in the RMAB setting to design selection algorithms that manage to satisfy the proposed fairness constraint. Our method, referred to as SoftFair, also provides theoretical performance guarantees and is asymptotically optimal. Finally, we demonstrate the utility of our approaches on simulated benchmarks and show that the soft fairness constraint can be handled without a significant sacrifice on value.

Owing to the benefits for customers (lower prices), drivers (higher revenues), aggregation companies (higher revenues) and the environment (fewer vehicles), on-demand ride pooling (e.g., Uber pool, Grab Share) has become quite popular. The significant computational complexity of matching vehicles to combinations of requests has meant that traditional ride pooling approaches are myopic in that they do not consider the impact of current matches on future value for vehicles/drivers. Recently, Neural Approximate Dynamic Programming (NeurADP) has employed value decomposition with Approximate Dynamic Programming (ADP) to outperform leading approaches by considering the impact of an individual agent's (vehicle) chosen actions on the future value of that agent. However, in order to ensure scalability and facilitate city-scale ride pooling, NeurADP completely ignores the impact of other agents actions on individual agent/vehicle value. As demonstrated in our experimental results, ignoring the impact of other agents actions on individual value can have a significant impact on the overall performance when there is increased competition among vehicles for demand. Our key contribution is a novel mechanism based on computing conditional expectations through joint conditional probabilities for capturing dependencies on other agents actions without increasing the complexity of training or decision making. We show that our new approach, Conditional Expectation based Value Decomposition (CEVD) outperforms NeurADP by up to 9.76% in terms of overall requests served, which is a significant improvement on a city wide benchmark taxi dataset.