相关论文: Policy Gradient with Tree Expansion

The advent of parameter-efficient fine-tuning methods has significantly reduced the computational burden of adapting large-scale pretrained models to diverse downstream tasks. However, existing approaches often struggle to achieve robust…

The policy gradient method enjoys the simplicity of the objective where the agent optimizes the cumulative reward directly. Moreover, in the continuous action domain, parameterized distribution of action distribution allows easy control of…

Ensuring fairness in machine learning remains a significant challenge, as models often inherit biases from their training data. Generative models have recently emerged as a promising approach to mitigate bias at the data level while…

Active Inference is a theory of action arising from neuroscience which casts action and planning as a bayesian inference problem to be solved by minimizing a single quantity - the variational free energy. Active Inference promises a…

Discrimination-aware classification aims to make accurate predictions while satisfying fairness constraints. Traditional decision tree learners typically optimize for information gain in the target attribute alone, which can result in…

Gradient-based methods have been widely used for system design and optimization in diverse application domains. Recently, there has been a renewed interest in studying theoretical properties of these methods in the context of control and…

We study the sequential decision making problem of maximizing the expected total reward while satisfying a constraint on the expected total utility. We employ the natural policy gradient method to solve the discounted infinite-horizon…

Sample inefficiency is a long-lasting problem in reinforcement learning (RL). The state-of-the-art estimates the optimal action values while it usually involves an extensive search over the state-action space and unstable optimization.…

Recent policy optimization approaches (Schulman et al., 2015a; 2017) have achieved substantial empirical successes by constructing new proxy optimization objectives. These proxy objectives allow stable and low variance policy learning, but…

Policy gradient methods, where one searches for the policy of interest by maximizing the value functions using first-order information, become increasingly popular for sequential decision making in reinforcement learning, games, and…

Gradients have been exploited in proposal distributions to accelerate the convergence of Markov chain Monte Carlo algorithms on discrete distributions. However, these methods require a natural differentiable extension of the target discrete…

We study the foundations of variational inference, which frames posterior inference as an optimisation problem, for probabilistic programming. The dominant approach for optimisation in practice is stochastic gradient descent. In particular,…

There is a growing desire in the field of reinforcement learning (and machine learning in general) to move from black-box models toward more "interpretable AI." We improve interpretability of reinforcement learning by increasing the utility…

Two of the leading approaches for model-free reinforcement learning are policy gradient methods and $Q$-learning methods. $Q$-learning methods can be effective and sample-efficient when they work, however, it is not well-understood why they…

Gradient boosted decision trees (GBDT) is the leading algorithm for many commercial and academic data applications. We give a deep analysis of this algorithm, especially the histogram technique, which is a basis for the regulized…

Natural policy gradient methods are popular reinforcement learning methods that improve the stability of policy gradient methods by utilizing second-order approximations to precondition the gradient with the inverse of the…

Most bandit policies are designed to either minimize regret in any problem instance, making very few assumptions about the underlying environment, or in a Bayesian sense, assuming a prior distribution over environment parameters. The former…

We propose Fractional Policy Gradients (FPG), a reinforcement learning framework incorporating fractional calculus for long-term temporal modeling in policy optimization. Standard policy gradient approaches face limitations from Markovian…

Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or sparse rewards. To tackle this problem, we present a…

Entropy augmented to reward is known to soften the greedy argmax policy to softmax policy. Entropy augmentation is reformulated and leads to a motivation to introduce an additional entropy term to the objective function in the form of…