Continuous time systems are often modeled using discrete time dynamics but this requires a small simulation step to maintain accuracy. In turn, this requires a large planning horizon which leads to computationally demanding planning problems and reduced performance. Previous work in model-free reinforcement learning has partially addressed this issue using action repeats where a policy is learned to determine a discrete action duration. Instead we propose to control the continuous decision timescale directly by using temporally-extended actions and letting the planner treat the duration of the action as an additional optimization variable along with the standard action variables. This additional structure has multiple advantages. It speeds up simulation time of trajectories and, importantly, it allows for deep horizon search in terms of primitive actions while using a shallow search depth in the planner. In addition, in the model-based reinforcement learning (MBRL) setting, it reduces compounding errors from model learning and improves training time for models. We show that this idea is effective and that the range for action durations can be automatically selected using a multi-armed bandit formulation and integrated into the MBRL framework. An extensive experimental evaluation both in planning and in MBRL, shows that our approach yields faster planning, better solutions, and that it enables solutions to problems that are not solved in the standard formulation.

Deep Reinforcement Learning (DRL) has achieved remarkable success in complex sequential decision-making tasks, such as playing Atari 2600 games and mastering board games. A critical yet underexplored aspect of DRL is the temporal scale of action execution. We propose a novel paradigm that integrates contextual bandits with DRL to adaptively select action durations, enhancing policy flexibility and computational efficiency. Our approach augments a Deep Q-Network (DQN) with a contextual bandit module that learns to choose optimal action repetition rates based on state contexts. Experiments on Atari 2600 games demonstrate significant performance improvements over static duration baselines, highlighting the efficacy of adaptive temporal abstractions in DRL. This paradigm offers a scalable solution for real-time applications like gaming and robotics, where dynamic action durations are critical.

This paper proposes a task planning framework for collaborative Human-Robot scenarios, specifically focused on assembling complex systems such as furniture. The human is characterized as an uncontrollable agent, implying for example that the agent is not bound by a pre-established sequence of actions and instead acts according to its own preferences. Meanwhile, the task planner computes reactively the optimal actions for the collaborative robot to efficiently complete the entire assembly task in the least time possible. We formalize the problem as a Discrete Event Markov Decision Problem (DE-MDP), a comprehensive framework that incorporates a variety of asynchronous behaviors, human change of mind and failure recovery as stochastic events. Although the problem could theoretically be addressed by constructing a graph of all possible actions, such an approach would be constrained by computational limitations. The proposed formulation offers an alternative solution utilizing Reinforcement Learning to derive an optimal policy for the robot. Experiments where conducted both in simulation and on a real system with human subjects assembling a chair in collaboration with a 7-DoF manipulator.

Traditional reinforcement learning (RL) generates discrete control policies, assigning one action per cycle. These policies are usually implemented as in a fixed-frequency control loop. This rigidity presents challenges as optimal control frequency is task-dependent; suboptimal frequencies increase computational demands and reduce exploration efficiency. Variable Time Step Reinforcement Learning (VTS-RL) addresses these issues with adaptive control frequencies, executing actions only when necessary, thus reducing computational load and extending the action space to include action durations. In this paper we introduce the Multi-Objective Soft Elastic Actor-Critic (MOSEAC) method to perform VTS-RL, validating it through theoretical analysis and experimentation in simulation and on real robots. Results show faster convergence, better training results, and reduced energy consumption with respect to other variable- or fixed-frequency approaches.

Traditional reinforcement learning (RL) methods typically employ a fixed control loop, where each cycle corresponds to an action. This rigidity poses challenges in practical applications, as the optimal control frequency is task-dependent. A suboptimal choice can lead to high computational demands and reduced exploration efficiency. Variable Time Step Reinforcement Learning (VTS-RL) addresses these issues by using adaptive frequencies for the control loop, executing actions only when necessary. This approach, rooted in reactive programming principles, reduces computational load and extends the action space by including action durations. However, VTS-RL's implementation is often complicated by the need to tune multiple hyperparameters that govern exploration in the multi-objective action-duration space (i.e., balancing task performance and number of time steps to achieve a goal). To overcome these challenges, we introduce the Multi-Objective Soft Elastic Actor-Critic (MOSEAC) method. This method features an adaptive reward scheme that adjusts hyperparameters based on observed trends in task rewards during training. This scheme reduces the complexity of hyperparameter tuning, requiring a single hyperparameter to guide exploration, thereby simplifying the learning process and lowering deployment costs. We validate the MOSEAC method through simulations in a Newtonian kinematics environment, demonstrating high task and training performance with fewer time steps, ultimately lowering energy consumption. This validation shows that MOSEAC streamlines RL algorithm deployment by automatically tuning the agent control loop frequency using a single parameter. Its principles can be applied to enhance any RL algorithm, making it a versatile solution for various applications.

This paper addresses exact approaches to multi-agent collective construction problem which tasks a group of cooperative agents to build a given structure in a blocksworld under the gravity constraint. We propose a generalization of the existing exact model based on mixed integer linear programming by accommodating varying agent action durations. We refer to the model as a fraction-time model. The generalization by introducing action duration enables one to create a more realistic model for various domains. It provides a significant reduction of plan execution duration at the cost of increased computational time, which rises steeply the closer the model gets to the exact real-world action duration. We also propose a makespan estimation function for the fraction-time model. This can be used to estimate the construction time reduction size for the purpose of cost-benefit analysis. The fraction-time model and the makespan estimation function have been evaluated in a series of experiments using a set of benchmark structures. The results show a significant reduction of plan execution duration for non-constant duration actions due to decreasing synchronization overhead at the end of each action. According to the results, the makespan estimation function provides a reasonably accurate estimate of the makespan.

Deep reinforcement learning (DRL) is becoming increasingly popular in implementing traffic signal control (TSC). However, most existing DRL methods employ fixed control strategies, making traffic signal phase duration less flexible. Additionally, the trend of using more complex DRL models makes real-life deployment more challenging. To address these two challenges, we firstly propose a two-stage DRL framework, named DynamicLight, which uses Max Queue-Length to select the proper phase and employs a deep Q-learning network to determine the duration of the corresponding phase. Based on the design of DynamicLight, we also introduce two variants: (1) DynamicLight-Lite, which addresses the first challenge by using only 19 parameters to achieve dynamic phase duration settings; and (2) DynamicLight-Cycle, which tackles the second challenge by actuating a set of phases in a fixed cyclical order to implement flexible phase duration in the respective cyclical phase structure. Numerical experiments are conducted using both real-world and synthetic datasets, covering four most commonly adopted traffic signal intersections in real life. Experimental results show that: (1) DynamicLight can learn satisfactorily on determining the phase duration and achieve a new state-of-the-art, with improvement up to 6% compared to the baselines in terms of adjusted average travel time; (2) DynamicLight-Lite matches or outperforms most baseline methods with only 19 parameters; and (3) DynamicLight-Cycle demonstrates high performance for current TSC systems without remarkable modification in an actual deployment. Our code is released at Github.

In reinforcement learning, continuous time is often discretized by a time scale $\delta$, to which the resulting performance is known to be highly sensitive. In this work, we seek to find a $\delta$-invariant algorithm for policy gradient (PG) methods, which performs well regardless of the value of $\delta$. We first identify the underlying reasons that cause PG methods to fail as $\delta \to 0$, proving that the variance of the PG estimator can diverge to infinity in stochastic environments under a certain assumption of stochasticity. While durative actions or action repetition can be employed to have $\delta$-invariance, previous action repetition methods cannot immediately react to unexpected situations in stochastic environments. We thus propose a novel $\delta$-invariant method named Safe Action Repetition (SAR) applicable to any existing PG algorithm. SAR can handle the stochasticity of environments by adaptively reacting to changes in states during action repetition. We empirically show that our method is not only $\delta$-invariant but also robust to stochasticity, outperforming previous $\delta$-invariant approaches on eight MuJoCo environments with both deterministic and stochastic settings. Our code is available at https://vision.snu.ac.kr/projects/sar.

Real world temporal planning often involves dealing with uncertainty about the duration of actions. In this paper, we describe a sound-and-complete compilation technique for strong planning that reduces any planning instance with uncertainty in the duration of actions to a plain temporal planning problem without uncertainty. We evaluate our technique by comparing it with a recent technique for PDDL domains with temporal uncertainty. The experimental results demonstrate the practical applicability of our approach and show complementary behavior with respect to previous techniques. We also demonstrate the high expressiveness of the translation by applying it to a significant fragment of the ANML language.