In robotics, contemporary strategies are learning-based, characterized by a complex black-box nature and a lack of interpretability, which may pose challenges in ensuring stability and safety. To address these issues, we propose integrating an obstacle-free deep reinforcement learning (DRL) trajectory planner with a novel auto-tuning low- and joint-level control strategy, all while actively engaging in the learning phase through interactions with the environment. This approach circumvents the complexities associated with computations while also addressing nonrepetitive and random obstacle avoidance tasks. First, a model-free DRL agent to plan velocity-bounded and obstacle-free motion is employed for a manipulator with 'n' degrees of freedom (DoF) in task space through joint-level reasoning. This plan is then input into a robust subsystem-based adaptive controller, which produces the necessary torques, while the Cuckoo Search Optimization (CSO) algorithm enhances control gains to minimize the time required to reach, time taken to stabilize, the maximum deviation from the desired value, and persistent tracking error in the steady state. This approach guarantees that position and velocity errors exponentially converge to zero in an unfamiliar environment, despite unknown robotic manipulator modeling. Theoretical assertions are validated through the presentation of simulation outcomes.

Building embodied agents on integrating Large Language Models (LLMs) and Reinforcement Learning (RL) have revolutionized human-AI interaction: researchers can now leverage language instructions to plan decision-making for open-ended tasks. However, existing research faces challenges in meeting the requirement of open-endedness. They typically either train LLM/RL models to adapt to a fixed counterpart, limiting exploration of novel skills and hindering the efficacy of human-AI interaction. To this end, we present OpenPAL, a co-training framework comprising two stages: (1) fine-tuning a pre-trained LLM to translate human instructions into goals for planning, and goal-conditioned training a policy for decision-making; (2) co-training to align the LLM and policy, achieving instruction open-endedness. We conducted experiments using Contra, an open-ended FPS game, demonstrating that an agent trained with OpenPAL not only comprehends arbitrary instructions but also exhibits efficient execution. These results suggest that OpenPAL holds the potential to construct open-ended embodied agents in practical scenarios.

We introduce Probabilistic Actor-Critic (PAC), a novel reinforcement learning algorithm with improved continuous control performance thanks to its ability to mitigate the exploration-exploitation trade-off. PAC achieves this by seamlessly integrating stochastic policies and critics, creating a dynamic synergy between the estimation of critic uncertainty and actor training. The key contribution of our PAC algorithm is that it explicitly models and infers epistemic uncertainty in the critic through Probably Approximately Correct-Bayesian (PAC-Bayes) analysis. This incorporation of critic uncertainty enables PAC to adapt its exploration strategy as it learns, guiding the actor's decision-making process. PAC compares favorably against fixed or pre-scheduled exploration schemes of the prior art. The synergy between stochastic policies and critics, guided by PAC-Bayes analysis, represents a fundamental step towards a more adaptive and effective exploration strategy in deep reinforcement learning. We report empirical evaluations demonstrating PAC's enhanced stability and improved performance over the state of the art in diverse continuous control problems.

In model-based reinforcement learning, most algorithms rely on simulating trajectories from one-step models of the dynamics learned on data. A critical challenge of this approach is the compounding of one-step prediction errors as the length of the trajectory grows. In this paper we tackle this issue by using a multi-step objective to train one-step models. Our objective is a weighted sum of the mean squared error (MSE) loss at various future horizons. We find that this new loss is particularly useful when the data is noisy (additive Gaussian noise in the observations), which is often the case in real-life environments. To support the multi-step loss, first we study its properties in two tractable cases: i) uni-dimensional linear system, and ii) two-parameter non-linear system. Second, we show in a variety of tasks (environments or datasets) that the models learned with this loss achieve a significant improvement in terms of the averaged R2-score on future prediction horizons. Finally, in the pure batch reinforcement learning setting, we demonstrate that one-step models serve as strong baselines when dynamics are deterministic, while multi-step models would be more advantageous in the presence of noise, highlighting the potential of our approach in real-world applications.

Explainable AI (XAI) has demonstrated the potential to help reinforcement learning (RL) practitioners to understand how RL models work. However, XAI for users who do not have RL expertise (non-RL experts), has not been studied sufficiently. This results in a difficulty for the non-RL experts to participate in the fundamental discussion of how RL models should be designed for an incoming society where humans and AI coexist. Solving such a problem would enable RL experts to communicate with the non-RL experts in producing machine learning solutions that better fit our society. We argue that abstracted trajectories, that depicts transitions between the major states of the RL model, will be useful for non-RL experts to build a mental model of the agents. Our early results suggest that by leveraging a visualization of the abstracted trajectories, users without RL expertise are able to infer the behavior patterns of RL.

Efficient utilization of the replay buffer plays a significant role in the off-policy actor-critic reinforcement learning (RL) algorithms used for model-free control policy synthesis for complex dynamical systems. We propose a method for achieving sample efficiency, which focuses on selecting unique samples and adding them to the replay buffer during the exploration with the goal of reducing the buffer size and maintaining the independent and identically distributed (IID) nature of the samples. Our method is based on selecting an important subset of the set of state variables from the experiences encountered during the initial phase of random exploration, partitioning the state space into a set of abstract states based on the selected important state variables, and finally selecting the experiences with unique state-reward combination by using a kernel density estimator. We formally prove that the off-policy actor-critic algorithm incorporating the proposed method for unique experience accumulation converges faster than the vanilla off-policy actor-critic algorithm. Furthermore, we evaluate our method by comparing it with two state-of-the-art actor-critic RL algorithms on several continuous control benchmarks available in the Gym environment. Experimental results demonstrate that our method achieves a significant reduction in the size of the replay buffer for all the benchmarks while achieving either faster convergent or better reward accumulation compared to the baseline algorithms.

We present a novel perspective on goal-conditioned reinforcement learning by framing it within the context of denoising diffusion models. Analogous to the diffusion process, where Gaussian noise is used to create random trajectories that walk away from the data manifold, we construct trajectories that move away from potential goal states. We then learn a goal-conditioned policy to reverse these deviations, analogously to the score function. This approach, which we call Merlin, can reach specified goals from an arbitrary initial state without learning a separate value function. In contrast to recent works utilizing diffusion models in offline RL, Merlin stands out as the first method to perform diffusion in the state space, requiring only one ``denoising" iteration per environment step. We experimentally validate our approach in various offline goal-reaching tasks, demonstrating substantial performance enhancements compared to state-of-the-art methods while improving computational efficiency over other diffusion-based RL methods by an order of magnitude. Our results suggest that this perspective on diffusion for RL is a simple, scalable, and practical direction for sequential decision making.

In this study, we present a transductive inference approach on that reward information propagation graph, which enables the effective estimation of rewards for unlabelled data in offline reinforcement learning. Reward inference is the key to learning effective policies in practical scenarios, while direct environmental interactions are either too costly or unethical and the reward functions are rarely accessible, such as in healthcare and robotics. Our research focuses on developing a reward inference method based on the contextual properties of information propagation on graphs that capitalizes on a constrained number of human reward annotations to infer rewards for unlabelled data. We leverage both the available data and limited reward annotations to construct a reward propagation graph, wherein the edge weights incorporate various influential factors pertaining to the rewards. Subsequently, we employ the constructed graph for transductive reward inference, thereby estimating rewards for unlabelled data. Furthermore, we establish the existence of a fixed point during several iterations of the transductive inference process and demonstrate its at least convergence to a local optimum. Empirical evaluations on locomotion and robotic manipulation tasks validate the effectiveness of our approach. The application of our inferred rewards improves the performance in offline reinforcement learning tasks.

Research in machine learning is making progress in fixing its own reproducibility crisis. Reinforcement learning (RL), in particular, faces its own set of unique challenges. Comparison of point estimates, and plots that show successful convergence to the optimal policy during training, may obfuscate overfitting or dependence on the experimental setup. Although researchers in RL have proposed reliability metrics that account for uncertainty to better understand each algorithm's strengths and weaknesses, the recommendations of past work do not assume the presence of out-of-distribution observations. We propose a set of evaluation methods that measure the robustness of RL algorithms under distribution shifts. The tools presented here argue for the need to account for performance over time while the agent is acting in its environment. In particular, we recommend time series analysis as a method of observational RL evaluation. We also show that the unique properties of RL and simulated dynamic environments allow us to make stronger assumptions to justify the measurement of causal impact in our evaluations. We then apply these tools to single-agent and multi-agent environments to show the impact of introducing distribution shifts during test time. We present this methodology as a first step toward rigorous RL evaluation in the presence of distribution shifts.

Bike-Sharing Systems provide eco-friendly urban mobility, contributing to the alleviation of traffic congestion and to healthier lifestyles. Efficiently operating such systems and maintaining high customer satisfaction is challenging due to the stochastic nature of trip demand, leading to full or empty stations. Devising effective rebalancing strategies using vehicles to redistribute bikes among stations is therefore of uttermost importance for operators. As a promising alternative to classical mathematical optimization, reinforcement learning is gaining ground to solve sequential decision-making problems. This paper introduces a spatio-temporal reinforcement learning algorithm for the dynamic rebalancing problem with multiple vehicles. We first formulate the problem as a Multi-agent Markov Decision Process in a continuous time framework. This allows for independent and cooperative vehicle rebalancing, eliminating the impractical restriction of time-discretized models where vehicle departures are synchronized. A comprehensive simulator under the first-arrive-first-serve rule is then developed to facilitate the learning process by computing immediate rewards under diverse demand scenarios. To estimate the value function and learn the rebalancing policy, various Deep Q-Network configurations are tested, minimizing the lost demand. Experiments are carried out on various datasets generated from historical data, affected by both temporal and weather factors. The proposed algorithms outperform benchmarks, including a multi-period Mixed-Integer Programming model, in terms of lost demand. Once trained, it yields immediate decisions, making it suitable for real-time applications. Our work offers practical insights for operators and enriches the integration of reinforcement learning into dynamic rebalancing problems, paving the way for more intelligent and robust urban mobility solutions.