Collaborative vehicle routing occurs when carriers collaborate through sharing their transportation requests and performing transportation requests on behalf of each other. This achieves economies of scale, thus reducing cost, greenhouse gas emissions and road congestion. But which carrier should partner with whom, and how much should each carrier be compensated? Traditional game theoretic solution concepts are expensive to calculate as the characteristic function scales exponentially with the number of agents. This would require solving the vehicle routing problem (NP-hard) an exponential number of times. We therefore propose to model this problem as a coalitional bargaining game solved using deep multi-agent reinforcement learning, where - crucially - agents are not given access to the characteristic function. Instead, we implicitly reason about the characteristic function; thus, when deployed in production, we only need to evaluate the expensive post-collaboration vehicle routing problem once. Our contribution is that we are the first to consider both the route allocation problem and gain sharing problem simultaneously - without access to the expensive characteristic function. Through decentralised machine learning, our agents bargain with each other and agree to outcomes that correlate well with the Shapley value - a fair profit allocation mechanism. Importantly, we are able to achieve a reduction in run-time of 88%.

Collaborative Vehicle Routing is where delivery companies cooperate by sharing their delivery information and performing delivery requests on behalf of each other. This achieves economies of scale and thus reduces cost, greenhouse gas emissions, and road congestion. But which company should partner with whom, and how much should each company be compensated? Traditional game theoretic solution concepts, such as the Shapley value or nucleolus, are difficult to calculate for the real-world problem of Collaborative Vehicle Routing due to the characteristic function scaling exponentially with the number of agents. This would require solving the Vehicle Routing Problem (an NP-Hard problem) an exponential number of times. We therefore propose to model this problem as a coalitional bargaining game where - crucially - agents are not given access to the characteristic function. Instead, we implicitly reason about the characteristic function, and thus eliminate the need to evaluate the VRP an exponential number of times - we only need to evaluate it once. Our contribution is that our decentralised approach is both scalable and considers the self-interested nature of companies. The agents learn using a modified Independent Proximal Policy Optimisation. Our RL agents outperform a strong heuristic bot. The agents correctly identify the optimal coalitions 79% of the time with an average optimality gap of 4.2% and reduction in run-time of 62%.

Recent curriculum Reinforcement Learning (RL) has shown notable progress in solving complex tasks by proposing sequences of surrogate tasks. However, the previous approaches often face challenges when they generate curriculum goals in a high-dimensional space. Thus, they usually rely on manually specified goal spaces. To alleviate this limitation and improve the scalability of the curriculum, we propose a novel curriculum method that automatically defines the semantic goal space which contains vital information for the curriculum process, and suggests curriculum goals over it. To define the semantic goal space, our method discretizes continuous observations via vector quantized-variational autoencoders (VQ-VAE) and restores the temporal relations between the discretized observations by a graph. Concurrently, ours suggests uncertainty and temporal distance-aware curriculum goals that converges to the final goals over the automatically composed goal space. We demonstrate that the proposed method allows efficient explorations in an uninformed environment with raw goal examples only. Also, ours outperforms the state-of-the-art curriculum RL methods on data efficiency and performance, in various goal-reaching tasks even with ego-centric visual inputs.

Offline reinforcement learning (RL) aims to optimize policy using collected data without online interactions. Model-based approaches are particularly appealing for addressing offline RL challenges due to their capability to mitigate the limitations of offline data through data generation using models. Prior research has demonstrated that introducing conservatism into the model or Q-function during policy optimization can effectively alleviate the prevalent distribution drift problem in offline RL. However, the investigation into the impacts of conservatism in reward estimation is still lacking. This paper proposes a novel model-based offline RL algorithm, Conservative Reward for model-based Offline Policy optimization (CROP), which conservatively estimates the reward in model training. To achieve a conservative reward estimation, CROP simultaneously minimizes the estimation error and the reward of random actions. Theoretical analysis shows that this conservative reward mechanism leads to a conservative policy evaluation and helps mitigate distribution drift. Experiments on D4RL benchmarks showcase that the performance of CROP is comparable to the state-of-the-art baselines. Notably, CROP establishes an innovative connection between offline and online RL, highlighting that offline RL problems can be tackled by adopting online RL techniques to the empirical Markov decision process trained with a conservative reward. The source code is available with https://github.com/G0K0URURI/CROP.git.

There have recently been significant advances in the problem of unsupervised object-centric representation learning and its application to downstream tasks. The latest works support the argument that employing disentangled object representations in image-based object-centric reinforcement learning tasks facilitates policy learning. We propose a novel object-centric reinforcement learning algorithm combining actor-critic and model-based approaches to utilize these representations effectively. In our approach, we use a transformer encoder to extract object representations and graph neural networks to approximate the dynamics of an environment. The proposed method fills a research gap in developing efficient object-centric world models for reinforcement learning settings that can be used for environments with discrete or continuous action spaces. Our algorithm performs better in a visually complex 3D robotic environment and a 2D environment with compositional structure than the state-of-the-art model-free actor-critic algorithm built upon transformer architecture and the state-of-the-art monolithic model-based algorithm.

We present a novel extension to the family of Soft Actor-Critic (SAC) algorithms. We argue that based on the Maximum Entropy Principle, discrete SAC can be further improved via additional statistical constraints derived from a surrogate critic policy. Furthermore, our findings suggests that these constraints provide an added robustness against potential domain shifts, which are essential for safe deployment of reinforcement learning agents in the real-world. We provide theoretical analysis and show empirical results on low data regimes for both in-distribution and out-of-distribution variants of Atari 2600 games.

In applying reinforcement learning (RL) to high-stakes domains, quantitative and qualitative evaluation using observational data can help practitioners understand the generalization performance of new policies. However, this type of off-policy evaluation (OPE) is inherently limited since offline data may not reflect the distribution shifts resulting from the application of new policies. On the other hand, online evaluation by collecting rollouts according to the new policy is often infeasible, as deploying new policies in these domains can be unsafe. In this work, we propose a semi-offline evaluation framework as an intermediate step between offline and online evaluation, where human users provide annotations of unobserved counterfactual trajectories. While tempting to simply augment existing data with such annotations, we show that this naive approach can lead to biased results. Instead, we design a new family of OPE estimators based on importance sampling (IS) and a novel weighting scheme that incorporate counterfactual annotations without introducing additional bias. We analyze the theoretical properties of our approach, showing its potential to reduce both bias and variance compared to standard IS estimators. Our analyses reveal important practical considerations for handling biased, noisy, or missing annotations. In a series of proof-of-concept experiments involving bandits and a healthcare-inspired simulator, we demonstrate that our approach outperforms purely offline IS estimators and is robust to imperfect annotations. Our framework, combined with principled human-centered design of annotation solicitation, can enable the application of RL in high-stakes domains.

While bisimulation-based approaches hold promise for learning robust state representations for Reinforcement Learning (RL) tasks, their efficacy in offline RL tasks has not been up to par. In some instances, their performance has even significantly underperformed alternative methods. We aim to understand why bisimulation methods succeed in online settings, but falter in offline tasks. Our analysis reveals that missing transitions in the dataset are particularly harmful to the bisimulation principle, leading to ineffective estimation. We also shed light on the critical role of reward scaling in bounding the scale of bisimulation measurements and of the value error they induce. Based on these findings, we propose to apply the expectile operator for representation learning to our offline RL setting, which helps to prevent overfitting to incomplete data. Meanwhile, by introducing an appropriate reward scaling strategy, we avoid the risk of feature collapse in representation space. We implement these recommendations on two state-of-the-art bisimulation-based algorithms, MICo and SimSR, and demonstrate performance gains on two benchmark suites: D4RL and Visual D4RL. Codes are provided at \url{https://github.com/zanghyu/Offline_Bisimulation}.

We propose the Thinker algorithm, a novel approach that enables reinforcement learning agents to autonomously interact with and utilize a learned world model. The Thinker algorithm wraps the environment with a world model and introduces new actions designed for interacting with the world model. These model-interaction actions enable agents to perform planning by proposing alternative plans to the world model before selecting a final action to execute in the environment. This approach eliminates the need for handcrafted planning algorithms by enabling the agent to learn how to plan autonomously and allows for easy interpretation of the agent's plan with visualization. We demonstrate the algorithm's effectiveness through experimental results in the game of Sokoban and the Atari 2600 benchmark, where the Thinker algorithm achieves state-of-the-art performance and competitive results, respectively. Visualizations of agents trained with the Thinker algorithm demonstrate that they have learned to plan effectively with the world model to select better actions. Thinker is the first work showing that an RL agent can learn to plan with a learned world model in complex environments.

In this paper, we present \textbf{C}ont\textbf{E}xtual \textbf{I}mitation \textbf{L}earning~(CEIL), a general and broadly applicable algorithm for imitation learning (IL). Inspired by the formulation of hindsight information matching, we derive CEIL by explicitly learning a hindsight embedding function together with a contextual policy using the hindsight embeddings. To achieve the expert matching objective for IL, we advocate for optimizing a contextual variable such that it biases the contextual policy towards mimicking expert behaviors. Beyond the typical learning from demonstrations (LfD) setting, CEIL is a generalist that can be effectively applied to multiple settings including: 1)~learning from observations (LfO), 2)~offline IL, 3)~cross-domain IL (mismatched experts), and 4) one-shot IL settings. Empirically, we evaluate CEIL on the popular MuJoCo tasks (online) and the D4RL dataset (offline). Compared to prior state-of-the-art baselines, we show that CEIL is more sample-efficient in most online IL tasks and achieves better or competitive performances in offline tasks.