Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer

Robot decision-making in partially observable, real-time, dynamic, and multi-agent environments remains a difficult and unsolved challenge. Model-free reinforcement learning (RL) is a promising approach to learning decision-making in such domains, however, end-to-end RL in complex environments is often intractable. To address this challenge in the RoboCup Standard Platform League (SPL) domain, we developed a novel architecture integrating RL within a classical robotics stack, while employing a multi-fidelity sim2real approach and decomposing behavior into learned sub-behaviors with heuristic selection. Our architecture led to victory in the 2024 RoboCup SPL Challenge Shield Division. In this work, we fully describe our system's architecture and empirically analyze key design decisions that contributed to its success. Our approach demonstrates how RL-based behaviors can be integrated into complete robot behavior architectures.

RL Zero: Zero-Shot Language to Behaviors without any Supervision

Rewards remain an uninterpretable way to specify tasks for Reinforcement Learning, as humans are often unable to predict the optimal behavior of any given reward function, leading to poor reward design and reward hacking. Language presents an appealing way to communicate intent to agents and bypass reward design, but prior efforts to do so have been limited by costly and unscalable labeling efforts. In this work, we propose a method for a completely unsupervised alternative to grounding language instructions in a zero-shot manner to obtain policies. We present a solution that takes the form of imagine, project, and imitate: The agent imagines the observation sequence corresponding to the language description of a task, projects the imagined sequence to our target domain, and grounds it to a policy. Video-language models allow us to imagine task descriptions that leverage knowledge of tasks learned from internet-scale video-text mappings. The challenge remains to ground these generations to a policy. In this work, we show that we can achieve a zero-shot language-to-behavior policy by first grounding the imagined sequences in real observations of an unsupervised RL agent and using a closed-form solution to imitation learning that allows the RL agent to mimic the grounded observations. Our method, RLZero, is the first to our knowledge to show zero-shot language to behavior generation abilities without any supervision on a variety of tasks on simulated domains. We further show that RLZero can also generate policies zero-shot from cross-embodied videos such as those scraped from YouTube.

Proto Successor Measure: Representing the Space of All Possible Solutions of Reinforcement Learning

Having explored an environment, intelligent agents should be able to transfer their knowledge to most downstream tasks within that environment. Referred to as "zero-shot learning," this ability remains elusive for general-purpose reinforcement learning algorithms. While recent works have attempted to produce zero-shot RL agents, they make assumptions about the nature of the tasks or the structure of the MDP. We present \emph{Proto Successor Measure}: the basis set for all possible solutions of Reinforcement Learning in a dynamical system. We provably show that any possible policy can be represented using an affine combination of these policy independent basis functions. Given a reward function at test time, we simply need to find the right set of linear weights to combine these basis corresponding to the optimal policy. We derive a practical algorithm to learn these basis functions using only interaction data from the environment and show that our approach can produce the optimal policy at test time for any given reward function without additional environmental interactions. Project page: https://agarwalsiddhant10.github.io/projects/psm.html.

Accelerating the discovery of steady-states of planetary interior dynamics with machine learning

Simulating mantle convection often requires reaching a computationally expensive steady-state, crucial for deriving scaling laws for thermal and dynamical flow properties and benchmarking numerical solutions. The strong temperature dependence of the rheology of mantle rocks causes viscosity variations of several orders of magnitude, leading to a slow-evolving stagnant lid where heat conduction dominates, overlying a rapidly-evolving and strongly convecting region. Time-stepping methods, while effective for fluids with constant viscosity, are hindered by the Courant criterion, which restricts the time step based on the system's maximum velocity and grid size. Consequently, achieving steady-state requires a large number of time steps due to the disparate time scales governing the stagnant and convecting regions. We present a concept for accelerating mantle convection simulations using machine learning. We generate a dataset of 128 two-dimensional simulations with mixed basal and internal heating, and pressure- and temperature-dependent viscosity. We train a feedforward neural network on 97 simulations to predict steady-state temperature profiles. These can then be used to initialize numerical time stepping methods for different simulation parameters. Compared to typical initializations, the number of time steps required to reach steady-state is reduced by a median factor of 3.75. The benefit of this method lies in requiring very few simulations to train on, providing a solution with no prediction error as we initialize a numerical method, and posing minimal computational overhead at inference time. We demonstrate the effectiveness of our approach and discuss the potential implications for accelerated simulations for advancing mantle convection research.

Aero-Nef: Neural Fields for Rapid Aircraft Aerodynamics Simulations

This paper presents a methodology to learn surrogate models of steady state fluid dynamics simulations on meshed domains, based on Implicit Neural Representations (INRs). The proposed models can be applied directly to unstructured domains for different flow conditions, handle non-parametric 3D geometric variations, and generalize to unseen shapes at test time. The coordinate-based formulation naturally leads to robustness with respect to discretization, allowing an excellent trade-off between computational cost (memory footprint and training time) and accuracy. The method is demonstrated on two industrially relevant applications: a RANS dataset of the two-dimensional compressible flow over a transonic airfoil and a dataset of the surface pressure distribution over 3D wings, including shape, inflow condition, and control surface deflection variations. On the considered test cases, our approach achieves a more than three times lower test error and significantly improves generalization error on unseen geometries compared to state-of-the-art Graph Neural Network architectures. Remarkably, the method can perform inference five order of magnitude faster than the high fidelity solver on the RANS transonic airfoil dataset. Code is available at https://gitlab.isae-supaero.fr/gi.catalani/aero-nepf

MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing

Memes have evolved as a prevalent medium for diverse communication, ranging from humour to propaganda. With the rising popularity of image-focused content, there is a growing need to explore its potential harm from different aspects. Previous studies have analyzed memes in closed settings - detecting harm, applying semantic labels, and offering natural language explanations. To extend this research, we introduce MemeMQA, a multimodal question-answering framework aiming to solicit accurate responses to structured questions while providing coherent explanations. We curate MemeMQACorpus, a new dataset featuring 1,880 questions related to 1,122 memes with corresponding answer-explanation pairs. We further propose ARSENAL, a novel two-stage multimodal framework that leverages the reasoning capabilities of LLMs to address MemeMQA. We benchmark MemeMQA using competitive baselines and demonstrate its superiority - ~18% enhanced answer prediction accuracy and distinct text generation lead across various metrics measuring lexical and semantic alignment over the best baseline. We analyze ARSENAL's robustness through diversification of question-set, confounder-based evaluation regarding MemeMQA's generalizability, and modality-specific assessment, enhancing our understanding of meme interpretation in the multimodal communication landscape.

Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning

Reinforcement Learning is a promising tool for learning complex policies even in fast-moving and object-interactive domains where human teleoperation or hard-coded policies might fail. To effectively reflect this challenging category of tasks, we introduce a dynamic, interactive RL testbed based on robot air hockey. By augmenting air hockey with a large family of tasks ranging from easy tasks like reaching, to challenging ones like pushing a block by hitting it with a puck, as well as goal-based and human-interactive tasks, our testbed allows a varied assessment of RL capabilities. The robot air hockey testbed also supports sim-to-real transfer with three domains: two simulators of increasing fidelity and a real robot system. Using a dataset of demonstration data gathered through two teleoperation systems: a virtualized control environment, and human shadowing, we assess the testbed with behavior cloning, offline RL, and RL from scratch.

$f$-Policy Gradients: A General Framework for Goal Conditioned RL using $f$-Divergences

Goal-Conditioned Reinforcement Learning (RL) problems often have access to sparse rewards where the agent receives a reward signal only when it has achieved the goal, making policy optimization a difficult problem. Several works augment this sparse reward with a learned dense reward function, but this can lead to sub-optimal policies if the reward is misaligned. Moreover, recent works have demonstrated that effective shaping rewards for a particular problem can depend on the underlying learning algorithm. This paper introduces a novel way to encourage exploration called $f$-Policy Gradients, or $f$-PG. $f$-PG minimizes the f-divergence between the agent's state visitation distribution and the goal, which we show can lead to an optimal policy. We derive gradients for various f-divergences to optimize this objective. Our learning paradigm provides dense learning signals for exploration in sparse reward settings. We further introduce an entropy-regularized policy optimization objective, that we call $state$-MaxEnt RL (or $s$-MaxEnt RL) as a special case of our objective. We show that several metric-based shaping rewards like L2 can be used with $s$-MaxEnt RL, providing a common ground to study such metric-based shaping rewards with efficient exploration. We find that $f$-PG has better performance compared to standard policy gradient methods on a challenging gridworld as well as the Point Maze and FetchReach environments. More information on our website https://agarwalsiddhant10.github.io/projects/fpg.html.

What do you MEME? Generating Explanations for Visual Semantic Role Labelling in Memes

Memes are powerful means for effective communication on social media. Their effortless amalgamation of viral visuals and compelling messages can have far-reaching implications with proper marketing. Previous research on memes has primarily focused on characterizing their affective spectrum and detecting whether the meme's message insinuates any intended harm, such as hate, offense, racism, etc. However, memes often use abstraction, which can be elusive. Here, we introduce a novel task - EXCLAIM, generating explanations for visual semantic role labeling in memes. To this end, we curate ExHVV, a novel dataset that offers natural language explanations of connotative roles for three types of entities - heroes, villains, and victims, encompassing 4,680 entities present in 3K memes. We also benchmark ExHVV with several strong unimodal and multimodal baselines. Moreover, we posit LUMEN, a novel multimodal, multi-task learning framework that endeavors to address EXCLAIM optimally by jointly learning to predict the correct semantic roles and correspondingly to generate suitable natural language explanations. LUMEN distinctly outperforms the best baseline across 18 standard natural language generation evaluation metrics. Our systematic evaluation and analyses demonstrate that characteristic multimodal cues required for adjudicating semantic roles are also helpful for generating suitable explanations.

Reinforcement Explanation Learning

Deep Learning has become overly complicated and has enjoyed stellar success in solving several classical problems like image classification, object detection, etc. Several methods for explaining these decisions have been proposed. Black-box methods to generate saliency maps are particularly interesting due to the fact that they do not utilize the internals of the model to explain the decision. Most black-box methods perturb the input and observe the changes in the output. We formulate saliency map generation as a sequential search problem and leverage upon Reinforcement Learning (RL) to accumulate evidence from input images that most strongly support decisions made by a classifier. Such a strategy encourages to search intelligently for the perturbations that will lead to high-quality explanations. While successful black box explanation approaches need to rely on heavy computations and suffer from small sample approximation, the deterministic policy learned by our method makes it a lot more efficient during the inference. Experiments on three benchmark datasets demonstrate the superiority of the proposed approach in inference time over state-of-the-arts without hurting the performance. Project Page: https://cvir.github.io/projects/rexl.html