More Like this

1. Meta-Learning Parameterized Skills

   Fu, Hoatian; Yu, Shangqun; Tiwari, Saket; Littman, Michael; Konidaris, George (July 2023, Proceedings of the Fortieth International Conference on Machine Learning)

   We propose a novel parameterized skill-learning algorithm that aims to learn transferable parameterized skills and synthesize them into a new action space that supports efficient learning in long-horizon tasks. We propose to leverage off-policy Meta-RL combined with a trajectory-centric smoothness term to learn a set of parameterized skills. Our agent can use these learned skills to construct a three-level hierarchical framework that models a Temporally-extended Parameterized Action Markov Decision Process. We empirically demonstrate that the proposed algorithms enable an agent to solve a set of difficult long-horizon (obstacle-course and robot manipulation) tasks. 

   more » « less
2. Reward-Guided Synthesis of Intelligent Agents with Control Structures

   https://doi.org/10.1145/3656447  

   Cui, Guofeng; Wang, Yuning; Qiu, Wenjie; Zhu, He (June 2024, Proceedings of the ACM on Programming Languages)

   Deep reinforcement learning (RL) has led to encouraging successes in numerous challenging robotics applications. However, the lack of inductive biases to support logic deduction and generalization in the representation of a deep RL model causes it less effective in exploring complex long-horizon robot-control tasks with sparse reward signals. Existing program synthesis algorithms for RL problems inherit the same limitation, as they either adapt conventional RL algorithms to guide program search or synthesize robot-control programs to imitate an RL model. We propose ReGuS, a reward-guided synthesis paradigm, to unlock the potential of program synthesis to overcome the exploration challenges. We develop a novel hierarchical synthesis algorithm with decomposed search space for loops, on-demand synthesis of conditional statements, and curriculum synthesis for procedure calls, to effectively compress the exploration space for long-horizon, multi-stage, and procedural robot-control tasks that are difficult to address by conventional RL techniques. Experiment results demonstrate that ReGuS significantly outperforms state-of-the-art RL algorithms and standard program synthesis baselines on challenging robot tasks including autonomous driving, locomotion control, and object manipulation. CCS Concepts: •Software and its engineering → Automatic programming. 

   more » « less
3. SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

   Lee, Kimin; Laskin, Michael; Srinivas, Aravind; Abbeel, Pieter (July 2021, International Conference on Machine Learning)

   null (Ed.)

   Off-policy deep reinforcement learning (RL) has been successful in a range of challenging domains. However, standard off-policy RL algorithms can suffer from several issues, such as instability in Qlearning and balancing exploration and exploitation. To mitigate these issues, we present SUNRISE, a simple unified ensemble method, which is compatible with various off-policy RL algorithms. SUNRISE integrates two key ingredients: (a) ensemble-based weighted Bellman backups, which re-weight target Q-values based on uncertainty estimates from a Q-ensemble, and (b) an inference method that selects actions using the highest upper-confidence bounds for efficient exploration. By enforcing the diversity between agents using Bootstrap with random initialization, we show that these different ideas are largely orthogonal and can be fruitfully integrated, together further improving the performance of existing off-policy RL algorithms, such as Soft Actor-Critic and Rainbow DQN, for both continuous and discrete control tasks on both low-dimensional and high-dimensional environments. 

   more » « less
4. Model-based Lifelong Reinforcement Learning with Bayesian Exploration

   Fu, H; Yu, S; Littman, ML; Konidaris, GD (December 2022, Advances in Neural Information Processing Systems 35)

   We propose a model-based lifelong reinforcement-learning approach that estimates a hierarchical Bayesian posterior distilling the common structure shared across different tasks. The learned posterior combined with a sample-based Bayesian exploration procedure increases the sample efficiency of learning across a family of related tasks. We first derive an analysis of the relationship between the sample complexity and the initialization quality of the posterior in the finite MDP setting. We next scale the approach to continuous-state domains by introducing a Variational Bayesian Lifelong Reinforcement Learning algorithm that can be combined with recent model-based deep RL methods, and that exhibits backward transfer. Experimental results on several challenging domains show that our algorithms achieve both better forward and backward transfer performance than state-of-the-art lifelong RL methods 

   more » « less
5. Multi-Objective Evolutionary Architecture Search for Parameterized Quantum Circuits

   https://doi.org/10.3390/e25010093  

   Ding, Li; Spector, Lee (January 2023, Entropy)

   Recent work on hybrid quantum-classical machine learning systems has demonstrated success in utilizing parameterized quantum circuits (PQCs) to solve the challenging reinforcement learning (RL) tasks, with provable learning advantages over classical systems, e.g., deep neural networks. While existing work demonstrates and exploits the strength of PQC-based models, the design choices of PQC architectures and the interactions between different quantum circuits on learning tasks are generally underexplored. In this work, we introduce a Multi-objective Evolutionary Architecture Search framework for parameterized quantum circuits (MEAS-PQC), which uses a multi-objective genetic algorithm with quantum-specific configurations to perform efficient searching of optimal PQC architectures. Experimental results show that our method can find architectures that have superior learning performance on three benchmark RL tasks, and are also optimized for additional objectives including reductions in quantum noise and model size. Further analysis of patterns and probability distributions of quantum operations helps identify performance-critical design choices of hybrid quantum-classical learning systems. 

   more » « less