Vision-driven autonomous flight and obstacle avoidance of Unmanned Aerial Vehicles (UAVs) along complex riverine environments for tasks like rescue and surveillance requires a robust control policy, which is yet difficult to obtain due to the shortage of trainable river environment simulators and reward sparsity in such environments. To easily verify the navigation controller performance for the river following task before real-world deployment, we developed a trainable photo-realistic dynamics-free riverine simulation environment using Unity. Successful river following trajectories in the environment are manually collected and Behavior Clone (BC) is used to train an Imitation Learning (IL) agent to mimic expert behavior and generate expert guidance. Finally, a framework is proposed to train a Deep Reinforcement Learning (DRL) agent using BC expert guidance and improve the expert policy online by sampling good demonstrations produced by the DRL to increase convergence rate and policy performance. This framework is able to solve the along-river autonomous navigation task and outperform baseline RL and IL methods. The code and trainable environments are available.

Deploying controllers trained with Reinforcement Learning (RL) on real robots can be challenging: RL relies on agents' policies being modeled as Markov Decision Processes (MDPs), which assume an inherently discrete passage of time. The use of MDPs results in that nearly all RL-based control systems employ a fixed-rate control strategy with a period (or time step) typically chosen based on the developer's experience or specific characteristics of the application environment. Unfortunately, the system should be controlled at the highest, worst-case frequency to ensure stability, which can demand significant computational and energy resources and hinder the deployability of the controller on onboard hardware. Adhering to the principles of reactive programming, we surmise that applying control actions only when necessary enables the use of simpler hardware and helps reduce energy consumption. We challenge the fixed frequency assumption by proposing a variant of RL with variable control rate. In this approach, the policy decides the action the agent should take as well as the duration of the time step associated with that action. In our new setting, we expand Soft Actor-Critic (SAC) to compute the optimal policy with a variable control rate, introducing the Soft Elastic Actor-Critic (SEAC) algorithm. We show the efficacy of SEAC through a proof-of-concept simulation driving an agent with Newtonian kinematics. Our experiments show higher average returns, shorter task completion times, and reduced computational resources when compared to fixed rate policies.

Visuomotor policies, which learn control mechanisms directly from high-dimensional visual observations, confront challenges in adapting to new environments with intricate visual variations. Data augmentation emerges as a promising method for bridging these generalization gaps by enriching data variety. However, straightforwardly augmenting the entire observation shall impose excessive burdens on policy learning and may even result in performance degradation. In this paper, we propose to improve the generalization ability of visuomotor policies as well as preserve training stability from two aspects: 1) We learn a control-aware mask through a self-supervised reconstruction task with three auxiliary losses and then apply strong augmentation only to those control-irrelevant regions based on the mask to reduce the generalization gaps. 2) To address training instability issues prevalent in visual reinforcement learning (RL), we distill the knowledge from a pretrained RL expert processing low-level environment states, to the student visuomotor policy. The policy is subsequently deployed to unseen environments without any further finetuning. We conducted comparison and ablation studies across various benchmarks: the DMControl Generalization Benchmark (DMC-GB), the enhanced Robot Manipulation Distraction Benchmark (RMDB), and a specialized long-horizontal drawer-opening robotic task. The extensive experimental results well demonstrate the effectiveness of our method, e.g., showing a 17\% improvement over previous methods in the video-hard setting of DMC-GB.

Robot learning tasks are extremely compute-intensive and hardware-specific. Thus the avenues of tackling these challenges, using a diverse dataset of offline demonstrations that can be used to train robot manipulation agents, is very appealing. The Train-Offline-Test-Online (TOTO) Benchmark provides a well-curated open-source dataset for offline training comprised mostly of expert data and also benchmark scores of the common offline-RL and behaviour cloning agents. In this paper, we introduce DiffClone, an offline algorithm of enhanced behaviour cloning agent with diffusion-based policy learning, and measured the efficacy of our method on real online physical robots at test time. This is also our official submission to the Train-Offline-Test-Online (TOTO) Benchmark Challenge organized at NeurIPS 2023. We experimented with both pre-trained visual representation and agent policies. In our experiments, we find that MOCO finetuned ResNet50 performs the best in comparison to other finetuned representations. Goal state conditioning and mapping to transitions resulted in a minute increase in the success rate and mean-reward. As for the agent policy, we developed DiffClone, a behaviour cloning agent improved using conditional diffusion.

Homeostasis is a biological process by which living beings maintain their internal balance. Previous research suggests that homeostasis is a learned behaviour. Recently introduced Homeostatic Regulated Reinforcement Learning (HRRL) framework attempts to explain this learned homeostatic behavior by linking Drive Reduction Theory and Reinforcement Learning. This linkage has been proven in the discrete time-space, but not in the continuous time-space. In this work, we advance the HRRL framework to a continuous time-space environment and validate the CTCS-HRRL (Continuous Time Continuous Space HRRL) framework. We achieve this by designing a model that mimics the homeostatic mechanisms in a real-world biological agent. This model uses the Hamilton-Jacobian Bellman Equation, and function approximation based on neural networks and Reinforcement Learning. Through a simulation-based experiment we demonstrate the efficacy of this model and uncover the evidence linked to the agent's ability to dynamically choose policies that favor homeostasis in a continuously changing internal-state milieu. Results of our experiments demonstrate that agent learns homeostatic behaviour in a CTCS environment, making CTCS-HRRL a promising framework for modellng animal dynamics and decision-making.

In an era of digital ubiquity, efficient resource management and decision-making are paramount across numerous industries. To this end, we present a comprehensive study on the integration of machine learning (ML) techniques into Huawei Cloud's OptVerse AI Solver, which aims to mitigate the scarcity of real-world mathematical programming instances, and to surpass the capabilities of traditional optimization techniques. We showcase our methods for generating complex SAT and MILP instances utilizing generative models that mirror multifaceted structures of real-world problem. Furthermore, we introduce a training framework leveraging augmentation policies to maintain solvers' utility in dynamic environments. Besides the data generation and augmentation, our proposed approaches also include novel ML-driven policies for personalized solver strategies, with an emphasis on applications like graph convolutional networks for initial basis selection and reinforcement learning for advanced presolving and cut selection. Additionally, we detail the incorporation of state-of-the-art parameter tuning algorithms which markedly elevate solver performance. Compared with traditional solvers such as Cplex and SCIP, our ML-augmented OptVerse AI Solver demonstrates superior speed and precision across both established benchmarks and real-world scenarios, reinforcing the practical imperative and effectiveness of machine learning techniques in mathematical programming solvers.

We improve several worst-case bounds for various online learning scenarios from (Auer and Long, Machine Learning, 1999). In particular, we sharpen an upper bound for delayed ambiguous reinforcement learning by a factor of 2 and an upper bound for learning compositions of families of functions by a factor of 2.41. We also improve a lower bound from the same paper for learning compositions of $k$ families of functions by a factor of $\Theta(\ln{k})$, matching the upper bound up to a constant factor. In addition, we solve a problem from (Long, Theoretical Computer Science, 2020) on the price of bandit feedback with respect to standard feedback for multiclass learning, and we improve an upper bound from (Feng et al., Theoretical Computer Science, 2023) on the price of $r$-input delayed ambiguous reinforcement learning by a factor of $r$, matching a lower bound from the same paper up to the leading term.

This paper introduces a reinforcement learning (RL) approach to address the challenges associated with configuring and optimizing genetic algorithms (GAs) for solving difficult combinatorial or non-linear problems. The proposed RL+GA method was specifically tested on the flow shop scheduling problem (FSP). The hybrid algorithm incorporates neural networks (NN) and uses the off-policy method Q-learning or the on-policy method Sarsa(0) to control two key genetic algorithm (GA) operators: parent selection mechanism and mutation. At each generation, the RL agent's action is determining the selection method, the probability of the parent selection and the probability of the offspring mutation. This allows the RL agent to dynamically adjust the selection and mutation based on its learned policy. The results of the study highlight the effectiveness of the RL+GA approach in improving the performance of the primitive GA. They also demonstrate its ability to learn and adapt from population diversity and solution improvements over time. This adaptability leads to improved scheduling solutions compared to static parameter configurations while maintaining population diversity throughout the evolutionary process.

We introduce BridgeData V2, a large and diverse dataset of robotic manipulation behaviors designed to facilitate research on scalable robot learning. BridgeData V2 contains 60,096 trajectories collected across 24 environments on a publicly available low-cost robot. BridgeData V2 provides extensive task and environment variability, leading to skills that can generalize across environments, domains, and institutions, making the dataset a useful resource for a broad range of researchers. Additionally, the dataset is compatible with a wide variety of open-vocabulary, multi-task learning methods conditioned on goal images or natural language instructions. In our experiments, we train 6 state-of-the-art imitation learning and offline reinforcement learning methods on our dataset, and find that they succeed on a suite of tasks requiring varying amounts of generalization. We also demonstrate that the performance of these methods improves with more data and higher capacity models, and that training on a greater variety of skills leads to improved generalization. By publicly sharing BridgeData V2 and our pre-trained models, we aim to accelerate research in scalable robot learning methods. Project page at https://rail-berkeley.github.io/bridgedata

Language is often considered a key aspect of human thinking, providing us with exceptional abilities to generalize, explore, plan, replan, and adapt to new situations. However, Reinforcement Learning (RL) agents are far from human-level performance in any of these abilities. We hypothesize one reason for such cognitive deficiencies is that they lack the benefits of thinking in language and that we can improve AI agents by training them to think like humans do. We introduce a novel Imitation Learning framework, Thought Cloning, where the idea is to not just clone the behaviors of human demonstrators, but also the thoughts humans have as they perform these behaviors. While we expect Thought Cloning to truly shine at scale on internet-sized datasets of humans thinking out loud while acting (e.g. online videos with transcripts), here we conduct experiments in a domain where the thinking and action data are synthetically generated. Results reveal that Thought Cloning learns much faster than Behavioral Cloning and its performance advantage grows the further out of distribution test tasks are, highlighting its ability to better handle novel situations. Thought Cloning also provides important benefits for AI Safety and Interpretability, and makes it easier to debug and improve AI. Because we can observe the agent's thoughts, we can (1) more easily diagnose why things are going wrong, making it easier to fix the problem, (2) steer the agent by correcting its thinking, or (3) prevent it from doing unsafe things it plans to do. Overall, by training agents how to think as well as behave, Thought Cloning creates safer, more powerful agents.