Related papers: Conservative DDPG -- Pessimistic RL without Ensemb…
Machine learning is shifting towards general-purpose pretrained generative models, trained in a self-supervised manner on large amounts of data, which can then be applied to solve a large number of tasks. However, due to their generic…
Although Behavioral Cloning (BC) in theory suffers compounding errors, its scalability and simplicity still makes it an attractive imitation learning algorithm. In contrast, imitation approaches with adversarial training typically does not…
Policy optimization methods are popular reinforcement learning algorithms, because their incremental and on-policy nature makes them more stable than the value-based counterparts. However, the same properties also make them slow to converge…
Policy constraint methods in offline reinforcement learning employ additional regularization techniques to constrain the discrepancy between the learned policy and the offline dataset. However, these methods tend to result in overly…
In this work, we consider the problem of network parameter optimization for rate maximization. We frame this as a joint optimization problem of power control, beam forming, and interference cancellation. We consider the setting where…
Reinforcement learning (RL) is pivotal for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, existing dLLM policy optimization methods suffer from two critical reliability bottlenecks: (1) reward…
We leverage the idea of a statistical ensemble to improve the quality of quantum annealing based binary compressive sensing. Since executing quantum machine instructions on a quantum annealer can result in an excited state, rather than the…
Classic no-regret multi-armed bandit algorithms, including the Upper Confidence Bound (UCB), Hedge, and EXP3, are inherently unfair by design. Their unfairness stems from their objective of playing the most rewarding arm as frequently as…
This paper presents our solution for the Real Robot Challenge (RRC) III, a competition featured in the NeurIPS 2022 Competition Track, aimed at addressing dexterous robotic manipulation tasks through learning from pre-collected offline…
Large Reasoning Models (LRMs) have shown exceptional reasoning capabilities, but they also suffer from the issue of overthinking, often generating excessively long and redundant answers. For problems that exceed the model's capabilities,…
In Reinforcement Learning (RL), agents aim at maximizing cumulative rewards in a given environment. During the learning process, RL agents face the dilemma of exploitation and exploration: leveraging existing knowledge to acquire rewards or…
While many algorithmic extensions to Deep Q-Networks (DQN) have been proposed, there remains limited understanding of how different improvements interact. In particular, multi-step and ensemble style extensions have shown promise in…
Model-based algorithms, which learn a dynamics model from logged experience and perform some sort of pessimistic planning under the learned model, have emerged as a promising paradigm for offline reinforcement learning (offline RL).…
Behavioral cloning (BC) provides a straightforward solution to offline RL by mimicking offline trajectories via supervised learning. Recent advances (Chen et al., 2021; Janner et al., 2021; Emmons et al., 2021) have shown that by…
Offline Reinforcement Learning (RL) suffers from the extrapolation error and value overestimation. From a generalization perspective, this issue can be attributed to the over-generalization of value functions or policies towards…
Inspired by Double Q-learning algorithm, the Double-DQN (DDQN) algorithm was originally proposed in order to address the overestimation issue in the original DQN algorithm. The DDQN has successfully shown both theoretically and empirically…
Multi-step (also called n-step) methods in reinforcement learning (RL) have been shown to be more efficient than the 1-step method due to faster propagation of the reward signal, both theoretically and empirically, in tasks exploiting…
This paper studies offline policy learning, which aims at utilizing observations collected a priori (from either fixed or adaptively evolving behavior policies) to learn an optimal individualized decision rule that achieves the best overall…
Overestimation bias control techniques are used by the majority of high-performing off-policy reinforcement learning algorithms. However, most of these techniques rely on pre-defined bias correction policies that are either not flexible…
Offline or batch reinforcement learning seeks to learn a near-optimal policy using history data without active exploration of the environment. To counter the insufficient coverage and sample scarcity of many offline datasets, the principle…