In this paper we introduce a novel algorithm-the Skill-Driven Skill Recombination Algorithm (SDSRA)--an innovative framework that significantly enhances the efficiency of achieving maximum entropy in reinforcement learning tasks. We find that SDSRA achieves faster convergence compared to the traditional Soft Actor-Critic (SAC) algorithm and produces improved policies. By integrating skill-based strategies within the robust Actor-Critic framework, SDSRA demonstrates remarkable adaptability and performance across a wide array of complex and diverse benchmarks. Reinforcement Learning (RL) has significantly advanced, with the Soft Actor-Critic (SAC) algorithm, introduced by Haarnoja et al. (2018), standing out for efficient exploration in complex tasks. Despite its strengths, SAC, like other RL methods, faces challenges in more intricate environments.

In this work, we investigate the means of using curiosity on replay buffers to improve offline multi-task continual reinforcement learning when tasks, which are defined by the non-stationarity in the environment, are non labeled and not evenly exposed to the learner in time. In particular, we investigate the use of curiosity both as a tool for task boundary detection and as a priority metric when it comes to retaining old transition tuples, which we respectively use to propose two different buffers. Firstly, we propose a Hybrid Reservoir Buffer with Task Separation (HRBTS), where curiosity is used to detect task boundaries that are not known due to the task agnostic nature of the problem. Secondly, by using curiosity as a priority metric when it comes to retaining old transition tuples, a Hybrid Curious Buffer (HCB) is proposed. We ultimately show that these buffers, in conjunction with regular reinforcement learning algorithms, can be used to alleviate the catastrophic forgetting issue suffered by the state of the art on replay buffers when the agent's exposure to tasks is not equal along time. We evaluate catastrophic forgetting and the efficiency of our proposed buffers against the latest works such as the Hybrid Reservoir Buffer (HRB) and the Multi-Time Scale Replay Buffer (MTR) in three different continual reinforcement learning settings. Experiments were done on classical control tasks and Metaworld environment. Experiments show that our proposed replay buffers display better immunity to catastrophic forgetting compared to existing works in most of the settings.

While there have been significant strides in dexterous manipulation, most of it is limited to benchmark tasks like in-hand reorientation which are of limited utility in the real world. The main benefit of dexterous hands over two-fingered ones is their ability to pickup tools and other objects (including thin ones) and grasp them firmly to apply force. However, this task requires both a complex understanding of functional affordances as well as precise low-level control. While prior work obtains affordances from human data this approach doesn't scale to low-level control. Similarly, simulation training cannot give the robot an understanding of real-world semantics. In this paper, we aim to combine the best of both worlds to accomplish functional grasping for in-the-wild objects. We use a modular approach. First, affordances are obtained by matching corresponding regions of different objects and then a low-level policy trained in sim is run to grasp it. We propose a novel application of eigengrasps to reduce the search space of RL using a small amount of human data and find that it leads to more stable and physically realistic motion. We find that eigengrasp action space beats baselines in simulation and outperforms hardcoded grasping in real and matches or outperforms a trained human teleoperator. Results visualizations and videos at https://dexfunc.github.io/

Advances in artificial intelligence (AI) have led to its application in many areas of everyday life. In the context of control engineering, reinforcement learning (RL) represents a particularly promising approach as it is centred around the idea of allowing an agent to freely interact with its environment to find an optimal strategy. One of the challenges professionals face when training and deploying RL agents is that the latter often have to run on dedicated embedded devices. This could be to integrate them into an existing toolchain or to satisfy certain performance criteria like real-time constraints. Conventional RL libraries, however, cannot be easily utilised in conjunction with that kind of hardware. In this paper, we present a framework named LExCI, the Learning and Experiencing Cycle Interface, which bridges this gap and provides end-users with a free and open-source tool for training agents on embedded systems using the open-source library RLlib. Its operability is demonstrated with two state-of-the-art RL-algorithms and a rapid control prototyping system.

In this work, we focus on addressing the long-horizon manipulation tasks in densely cluttered scenes. Such tasks require policies to effectively manage severe occlusions among objects and continually produce actions based on visual observations. We propose a vision-based Hierarchical policy for Cluttered-scene Long-horizon Manipulation (HCLM). It employs a high-level policy and three options to select and instantiate three parameterized action primitives: push, pick, and place. We first train the pick and place options by behavior cloning (BC). Subsequently, we use hierarchical reinforcement learning (HRL) to train the high-level policy and push option. During HRL, we propose a Spatially Extended Q-update (SEQ) to augment the updates for the push option and a Two-Stage Update Scheme (TSUS) to alleviate the non-stationary transition problem in updating the high-level policy. We demonstrate that HCLM significantly outperforms baseline methods in terms of success rate and efficiency in diverse tasks. We also highlight our method's ability to generalize to more cluttered environments with more additional blocks.

Multi-goal robot manipulation tasks with sparse rewards are difficult for reinforcement learning (RL) algorithms due to the inefficiency in collecting successful experiences. Recent algorithms such as Hindsight Experience Replay (HER) expedite learning by taking advantage of failed trajectories and replacing the desired goal with one of the achieved states so that any failed trajectory can be utilized as a contribution to learning. However, HER uniformly chooses failed trajectories, without taking into account which ones might be the most valuable for learning. In this paper, we address this problem and propose a novel approach Contact Energy Based Prioritization~(CEBP) to select the samples from the replay buffer based on rich information due to contact, leveraging the touch sensors in the gripper of the robot and object displacement. Our prioritization scheme favors sampling of contact-rich experiences, which are arguably the ones providing the largest amount of information. We evaluate our proposed approach on various sparse reward robotic tasks and compare them with the state-of-the-art methods. We show that our method surpasses or performs on par with those methods on robot manipulation tasks. Finally, we deploy the trained policy from our method to a real Franka robot for a pick-and-place task. We observe that the robot can solve the task successfully. The videos and code are publicly available at: https://erdiphd.github.io/HER_force

Agents trained with DQN rely on an observation at each timestep to decide what action to take next. However, in real world applications observations can change or be missing entirely. Examples of this could be a light bulb breaking down, or the wallpaper in a certain room changing. While these situations change the actual observation, the underlying optimal policy does not change. Because of this we want our agent to continue taking actions until it receives a (recognized) observation again. To achieve this we introduce a combination of a neural network architecture that uses hidden representations of the observations and a novel n-step loss function. Our implementation is able to withstand location based blindness stretches longer than the ones it was trained on, and therefore shows robustness to temporary blindness. For access to our implementation, please email Nathan, Marije, or Pau.

This study evaluates the application of a discrete action space reinforcement learning method (Q-learning) to the continuous control problem of robot inverted pendulum balancing. To speed up the learning process and to overcome technical difficulties related to the direct learning on the real robotic system, the learning phase is performed in simulation environment. A mathematical model of the system dynamics is implemented, deduced by curve fitting on data acquired from the real system. The proposed approach demonstrated feasible, featuring its application on a real world robot that learned to balance an inverted pendulum. This study also reinforces and demonstrates the importance of an accurate representation of the physical world in simulation to achieve a more efficient implementation of reinforcement learning algorithms in real world, even when using a discrete action space algorithm to control a continuous action.

The utilization of artificial intelligence (AI) in card games has been a well-explored subject within AI research for an extensive period. Recent advancements have propelled AI programs to showcase expertise in intricate card games such as Mahjong, DouDizhu, and Texas Hold'em. In this work, we aim to develop an AI program for an exceptionally complex and popular card game called GuanDan. This game involves four players engaging in both competitive and cooperative play throughout a long process to upgrade their level, posing great challenges for AI due to its expansive state and action space, long episode length, and complex rules. Employing reinforcement learning techniques, specifically Deep Monte Carlo (DMC), and a distributed training framework, we first put forward an AI program named DanZero for this game. Evaluation against baseline AI programs based on heuristic rules highlights the outstanding performance of our bot. Besides, in order to further enhance the AI's capabilities, we apply policy-based reinforcement learning algorithm to GuanDan. To address the challenges arising from the huge action space, which will significantly impact the performance of policy-based algorithms, we adopt the pre-trained model to facilitate the training process and the achieved AI program manages to achieve a superior performance.

The study addresses the foundational and challenging task of peg-in-hole assembly in robotics, where misalignments caused by sensor inaccuracies and mechanical errors often result in insertion failures or jamming. This research introduces PolyFit, representing a paradigm shift by transitioning from a reinforcement learning approach to a supervised learning methodology. PolyFit is a Force/Torque (F/T)-based supervised learning framework designed for 5-DoF peg-in-hole assembly. It utilizes F/T data for accurate extrinsic pose estimation and adjusts the peg pose to rectify misalignments. Extensive training in a simulated environment involves a dataset encompassing a diverse range of peg-hole shapes, extrinsic poses, and their corresponding contact F/T readings. To enhance extrinsic pose estimation, a multi-point contact strategy is integrated into the model input, recognizing that identical F/T readings can indicate different poses. The study proposes a sim-to-real adaptation method for real-world application, using a sim-real paired dataset to enable effective generalization to complex and unseen polygon shapes. PolyFit achieves impressive peg-in-hole success rates of 97.3% and 96.3% for seen and unseen shapes in simulations, respectively. Real-world evaluations further demonstrate substantial success rates of 86.7% and 85.0%, highlighting the robustness and adaptability of the proposed method.