In human societies, people often incorporate fairness in their decisions and treat reciprocally by being kind to those who act kindly. They evaluate the kindness of others' actions not only by monitoring the outcomes but also by considering the intentions. This behavioral concept can be adapted to train cooperative agents in Multi-Agent Reinforcement Learning (MARL). We propose the KindMARL method, where agents' intentions are measured by counterfactual reasoning over the environmental impact of the actions that were available to the agents. More specifically, the current environment state is compared with the estimation of the current environment state provided that the agent had chosen another action. The difference between each agent's reward, as the outcome of its action, with that of its fellow, multiplied by the intention of the fellow is then taken as the fellow's "kindness". If the result of each reward-comparison confirms the agent's superiority, it perceives the fellow's kindness and reduces its own reward. Experimental results in the Cleanup and Harvest environments show that training based on the KindMARL method enabled the agents to earn 89\% (resp. 37\%) and 44% (resp. 43\%) more total rewards than training based on the Inequity Aversion and Social Influence methods. The effectiveness of KindMARL is further supported by experiments in a traffic light control problem.

We address the issue of estimation bias in deep reinforcement learning (DRL) by introducing solution mechanisms that include a new, twin TD-regularized actor-critic (TDR) method. It aims at reducing both over and under-estimation errors. With TDR and by combining good DRL improvements, such as distributional learning and long N-step surrogate stage reward (LNSS) method, we show that our new TDR-based actor-critic learning has enabled DRL methods to outperform their respective baselines in challenging environments in DeepMind Control Suite. Furthermore, they elevate TD3 and SAC respectively to a level of performance comparable to that of D4PG (the current SOTA), and they also improve the performance of D4PG to a new SOTA level measured by mean reward, convergence speed, learning success rate, and learning variance.

Meta Reinforcement Learning (Meta RL) trains agents that adapt to fast-changing environments and tasks. Current strategies often lose adaption efficiency due to the passive nature of model exploration, causing delayed understanding of new transition dynamics. This results in particularly fast-evolving tasks being impossible to solve. We propose a novel approach, Hypothesis Network Planned Exploration (HyPE), that integrates an active and planned exploration process via the hypothesis network to optimize adaptation speed. HyPE uses a generative hypothesis network to form potential models of state transition dynamics, then eliminates incorrect models through strategically devised experiments. Evaluated on a symbolic version of the Alchemy game, HyPE outpaces baseline methods in adaptation speed and model accuracy, validating its potential in enhancing reinforcement learning adaptation in rapidly evolving settings.

Offline meta-reinforcement learning (OMRL) utilizes pre-collected offline datasets to enhance the agent's generalization ability on unseen tasks. However, the context shift problem arises due to the distribution discrepancy between the contexts used for training (from the behavior policy) and testing (from the exploration policy). The context shift problem leads to incorrect task inference and further deteriorates the generalization ability of the meta-policy. Existing OMRL methods either overlook this problem or attempt to mitigate it with additional information. In this paper, we propose a novel approach called Context Shift Reduction for OMRL (CSRO) to address the context shift problem with only offline datasets. The key insight of CSRO is to minimize the influence of policy in context during both the meta-training and meta-test phases. During meta-training, we design a max-min mutual information representation learning mechanism to diminish the impact of the behavior policy on task representation. In the meta-test phase, we introduce the non-prior context collection strategy to reduce the effect of the exploration policy. Experimental results demonstrate that CSRO significantly reduces the context shift and improves the generalization ability, surpassing previous methods across various challenging domains.

In the pursuit of autonomous spacecraft proximity maneuvers and docking(PMD), we introduce a novel Bayesian actor-critic reinforcement learning algorithm to learn a control policy with the stability guarantee. The PMD task is formulated as a Markov decision process that reflects the relative dynamic model, the docking cone and the cost function. Drawing from the principles of Lyapunov theory, we frame the temporal difference learning as a constrained Gaussian process regression problem. This innovative approach allows the state-value function to be expressed as a Lyapunov function, leveraging the Gaussian process and deep kernel learning. We develop a novel Bayesian quadrature policy optimization procedure to analytically compute the policy gradient while integrating Lyapunov-based stability constraints. This integration is pivotal in satisfying the rigorous safety demands of spaceflight missions. The proposed algorithm has been experimentally evaluated on a spacecraft air-bearing testbed and shows impressive and promising performance.

Robotic agents trained using reinforcement learning have the problem of taking unreliable actions in an out-of-distribution (OOD) state. Agents can easily become OOD in real-world environments because it is almost impossible for them to visit and learn the entire state space during training. Unfortunately, unreliable actions do not ensure that agents perform their original tasks successfully. Therefore, agents should be able to recognize whether they are in OOD states and learn how to return to the learned state distribution rather than continue to take unreliable actions. In this study, we propose a novel method for retraining agents to recover from OOD situations in a self-supervised manner when they fall into OOD states. Our in-depth experimental results demonstrate that our method substantially improves the agent's ability to recover from OOD situations in terms of sample efficiency and restoration of the performance for the original tasks. Moreover, we show that our method can retrain the agent to recover from OOD situations even when in-distribution states are difficult to visit through exploration.

In this study, we delve into the dynamic landscape of machine learning research evolution. Initially, through the utilization of Latent Dirichlet Allocation, we discern pivotal themes and fundamental concepts that have emerged within the realm of machine learning. Subsequently, we undertake a comprehensive analysis to track the evolutionary trajectories of these identified themes. To quantify the novelty and divergence of research contributions, we employ the Kullback-Leibler Divergence metric. This statistical measure serves as a proxy for ``surprise'', indicating the extent of differentiation between the content of academic papers and the subsequent developments in research. By amalgamating these insights, we gain the ability to ascertain the pivotal roles played by prominent researchers and the significance of specific academic venues (periodicals and conferences) within the machine learning domain.

Goal-conditioned planning benefits from learned low-dimensional representations of rich, high-dimensional observations. While compact latent representations, typically learned from variational autoencoders or inverse dynamics, enable goal-conditioned planning they ignore state affordances, thus hampering their sample-efficient planning capabilities. In this paper, we learn a representation that associates reachable states together for effective onward planning. We first learn a latent representation with multi-step inverse dynamics (to remove distracting information); and then transform this representation to associate reachable states together in $\ell_2$ space. Our proposals are rigorously tested in various simulation testbeds. Numerical results in reward-based and reward-free settings show significant improvements in sampling efficiency, and yields layered state abstractions that enable computationally efficient hierarchical planning.

This paper presents a novel method for learning reward functions for robotic motions by harnessing the power of a CLIP-based model. Traditional reward function design often hinges on manual feature engineering, which can struggle to generalize across an array of tasks. Our approach circumvents this challenge by capitalizing on CLIP's capability to process both state features and image inputs effectively. Given a pair of consecutive observations, our model excels in identifying the motion executed between them. We showcase results spanning various robotic activities, such as directing a gripper to a designated target and adjusting the position of a cube. Through experimental evaluations, we underline the proficiency of our method in precisely deducing motion and its promise to enhance reinforcement learning training in the realm of robotics. Reinforcement Learning (RL) distinguishes itself within the machine learning spectrum by enabling an agent to determine optimal decisions through interactions with an environment, while targeting maximal cumulative reward. The linchpin of this approach is the reward mechanism, which steers the agent's decision-making. Each reward, be it positive or negative, influences the agent's action choices. Essentially, the reward system is RL's guiding compass, directing the agent toward optimal actions and ensuring its adaptability in dynamic and unpredictable scenarios. Without it, the agent would drift aimlessly, unable to discern advantageous actions from detrimental ones.

Efficient exploration for an agent is challenging in reinforcement learning (RL). In this paper, a novel actor-critic framework namely virtual action actor-critic (VAAC), is proposed to address the challenge of efficient exploration in RL. This work is inspired by humans' ability to imagine the potential outcomes of their actions without actually taking them. In order to emulate this ability, VAAC introduces a new actor called virtual actor (VA), alongside the conventional actor-critic framework. Unlike the conventional actor, the VA takes the virtual action to anticipate the next state without interacting with the environment. With the virtual policy following a Gaussian distribution, the VA is trained to maximize the anticipated novelty of the subsequent state resulting from a virtual action. If any next state resulting from available actions does not exhibit high anticipated novelty, training the VA leads to an increase in the virtual policy entropy. Hence, high virtual policy entropy represents that there is no room for exploration. The proposed VAAC aims to maximize a modified Q function, which combines cumulative rewards and the negative sum of virtual policy entropy. Experimental results show that the VAAC improves the exploration performance compared to existing algorithms.