More Like this

1. Autonomous Learning in a Pseudo-Episodic Physical Environment

   https://doi.org/10.1007/s10846-022-01577-5  

   Haughn, Kevin P.; Inman, Daniel J. (February 2022, Journal of Intelligent & Robotic Systems)

   Abstract Forpractical considerations reinforcement learning has proven to be a difficult task outside of simulation when applied to a physical experiment. Here we derive an optional approach to model free reinforcement learning, achieved entirely online, through careful experimental design and algorithmic decision making. We design a reinforcement learning scheme to implement traditionally episodic algorithms for an unstable 1-dimensional mechanical environment. The training scheme is completely autonomous, requiring no human to be present throughout the learning process. We show that the pseudo-episodic technique allows for additional learning updates with off-policy actor-critic and experience replay methods. We show that including these additional updates between periods of traditional training episodes can improve speed and consistency of learning. Furthermore, we validate the procedure in experimental hardware. In the physical environment, several algorithm variants learned rapidly, each surpassing baseline maximum reward. The algorithms in this research are model free and use only information obtained by an onboard sensor during training. 

   more » « less
2. Fast Value Tracking for Deep Reinforcement Learning

   Shih, Frank; Liang, Faming (May 2024, The Twelfth International Conference on Learning Representations)

   Reinforcement learning (RL) tackles sequential decision-making problems by creating agents that interacts with their environment. However, existing algorithms often view these problem as static, focusing on point estimates for model parameters to maximize expected rewards, neglecting the stochastic dynamics of agent-environment interactions and the critical role of uncertainty quantification. Our research leverages the Kalman filtering paradigm to introduce a novel and scalable sampling algorithm called Langevinized Kalman Temporal-Difference (LKTD) for deep reinforcement learning. This algorithm, grounded in Stochastic Gradient Markov Chain Monte Carlo (SGMCMC), efficiently draws samples from the posterior distribution of deep neural network parameters. Under mild conditions, we prove that the posterior samples generated by the LKTD algorithm converge to a stationary distribution. This convergence not only enables us to quantify uncertainties associated with the value function and model parameters but also allows us to monitor these uncertainties during policy updates throughout the training phase. The LKTD algorithm paves the way for more robust and adaptable reinforcement learning approaches. 

   more » « less
3. Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning

   https://doi.org/10.1109/ICRA.2019.8793537  

   Schaff, Charles; Yunis, David; Chakrabarti, Ayan; Walter, Matthew R. (May 2019, Proceedings of the International Conference on Robotics and Automation (ICRA))

   The physical design of a robot and the policy that controls its motion are inherently coupled, and should be determined according to the task and environment. In an increasing number of applications, data-driven and learning-based approaches, such as deep reinforcement learning, have proven effective at designing control policies. For most tasks, the only way to evaluate a physical design with respect to such control policies is empirical---i.e., by picking a design and training a control policy for it. Since training these policies is time-consuming, it is computationally infeasible to train separate policies for all possible designs as a means to identify the best one. In this work, we address this limitation by introducing a method that jointly optimizes over the physical design and control network. Our approach maintains a distribution over designs and uses reinforcement learning to optimize a control policy to maximize expected reward over the design distribution. We give the controller access to design parameters to allow it to tailor its policy to each design in the distribution. Throughout training, we shift the distribution towards higher-performing designs, eventually converging to a design and control policy that are jointly optimal. We evaluate our approach in the context of legged locomotion, and demonstrate that it discovers novel designs and walking gaits, outperforming baselines across different settings. 

   more » « less
4. Efficient Reinforcement Learning with Hierarchies of Machines by Leveraging Internal Transitions

   https://doi.org/10.24963/ijcai.2017/196  

   Bai, A.; Russell, S. (August 2017, Twenty-Sixth International Joint Conference on Artificial Intelligence)

   In the context of hierarchical reinforcement learning, the idea of hierarchies of abstract machines (HAMs) is to write a partial policy as a set of hierarchical finite state machines with unspecified choice states, and use reinforcement learning to learn an optimal completion of this partial policy. Given a HAM with potentially deep hierarchical structure, there often exist many internal transitions where a machine calls another machine with the environment state unchanged. In this paper, we propose a new hierarchical reinforcement learning algorithm that discovers such internal transitions automatically, and shortcircuits them recursively in computation of Q values. The resulting HAMQ-INT algorithm outperforms the state of the art significantly on the benchmark Taxi domain and a much more complex RoboCup Keepaway domain. 

   more » « less
5. Federated Reinforcement Learning: Linear Speedup Under Markovian Sampling

   Khodadadian, Sajad; Sharma, Pranay; Joshi, Gauri; Maguluri, Siva Theja (January 2022, International Conference on Machine Learning)

   Since reinforcement learning algorithms are notoriously data-intensive, the task of sampling observations from the environment is usually split across multiple agents. However, transferring these observations from the agents to a central location can be prohibitively expensive in terms of the communication cost, and it can also compromise the privacy of each agent’s local behavior policy. In this paper, we consider a federated reinforcement learning framework where multiple agents collaboratively learn a global model, without sharing their individual data and policies. Each agent maintains a local copy of the model and updates it using locally sampled data. Although having N agents enables the sampling of N times more data, it is not clear if it leads to proportional convergence speedup. We propose federated versions of on-policy TD, off-policy TD and Q-learning, and analyze their convergence. For all these algorithms, to the best of our knowledge, we are the first to consider Markovian noise and multiple local updates, and prove a linear convergence speedup with respect to the number of agents. To obtain these results, we show that federated TD and Q-learning are special cases of a general framework for federated stochastic approximation with Markovian noise, and we leverage this framework to provide a unified convergence analysis that applies to all the algorithms. 

   more » « less