Related papers: Model-Free Opponent Shaping
Reinforcement learning (RL) algorithms can be divided into two classes: model-free algorithms, which are sample-inefficient, and model-based algorithms, which suffer from model bias. Dyna-style algorithms combine these two approaches by…
We study reinforcement learning in MDPs whose transition function is stochastic at most steps but may behave adversarially at a fixed subset of $\Lambda$ steps per episode. This model captures environments that are stable except at a few…
Federated Learning (FL) enables training of a global model from distributed data, while preserving data privacy. However, the singular-model based operation of FL is open with uploading poisoned models compatible with the global model…
The ability to walk in new scenarios is a key milestone on the path toward real-world applications of legged robots. In this work, we introduce Meta Strategy Optimization, a meta-learning algorithm for training policies with latent variable…
The process of robot design is a complex task and the majority of design decisions are still based on human intuition or tedious manual tuning. A more informed way of facing this task is computational design methods where design parameters…
As autonomous robots move into complex, dynamic real-world environments, they must learn to navigate safely in real time, yet anticipating all possible behaviors is infeasible. We propose a composable, model-free reinforcement learning…
We consider the problem of learning in adversarial Markov decision processes [MDPs] with an oblivious adversary in a full-information setting. The agent interacts with an environment during $T$ episodes, each of which consists of $H$…
Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this…
Reward shaping (RS) is a powerful method in reinforcement learning (RL) for overcoming the problem of sparse or uninformative rewards. However, RS typically relies on manually engineered shaping-reward functions whose construction is…
In this paper, we propose a new approach called MemLoss to improve the adversarial training of machine learning models. MemLoss leverages previously generated adversarial examples, referred to as 'Memory Adversarial Examples,' to enhance…
Multi-Agent Reinforcement Learning (MARL) considers settings in which a set of coexisting agents interact with one another and their environment. The adaptation and learning of other agents induces non-stationarity in the environment…
As an important psychological and social experiment, the Iterated Prisoner's Dilemma (IPD) treats the choice to cooperate or defect as an atomic action. We propose to study the behaviors of online learning algorithms in the Iterated…
Combining model-based and model-free learning systems has been shown to improve the sample efficiency of learning to perform complex robotic tasks. However, dual-system approaches fail to consider the reliability of the learned model when…
Many machine learning systems are built to solve the hardest examples of a particular task, which often makes them large and expensive to run---especially with respect to the easier examples, which might require much less computation. For…
This work developed a meta-learning approach that adapts the control policy on the fly to different changing conditions for robust locomotion. The proposed method constantly updates the interaction model, samples feasible sequences of…
Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There is considerable interest in designing reinforcement learning (RL) algorithms with similar properties. This includes…
Despite of the recent progress in agents that learn through interaction, there are several challenges in terms of sample efficiency and generalization across unseen behaviors during training. To mitigate these problems, we propose and apply…
Model-free reinforcement learning methods such as the Proximal Policy Optimization algorithm (PPO) have successfully applied in complex decision-making problems such as Atari games. However, these methods suffer from high variances and high…
In Multi-agent Reinforcement Learning (MARL), accurately perceiving opponents' strategies is essential for both cooperative and adversarial contexts, particularly within dynamic environments. While Proximal Policy Optimization (PPO) and…
Opponent modeling is essential to exploit sub-optimal opponents in strategic interactions. Most previous works focus on building explicit models to directly predict the opponents' styles or strategies, which require a large amount of data…