Related papers: Exploration by Random Network Distillation
We introduce a novel approach to large language model (LLM) distillation by formulating it as a constrained reinforcement learning problem. While recent work has begun exploring the integration of task-specific rewards into distillation…
Imitation learning in a high-dimensional environment is challenging. Most inverse reinforcement learning (IRL) methods fail to outperform the demonstrator in such a high-dimensional environment, e.g., Atari domain. To address this…
One of the bottlenecks preventing Deep Reinforcement Learning algorithms (DRL) from real-world applications is how to explore the environment and collect informative transitions efficiently. The present paper describes bounded exploration,…
We present the first reinforcement-learning model to self-improve its reward-modulated training implemented through a continuously improving "intuition" neural network. An agent was trained how to play the arcade video game Pong with two…
While deep reinforcement learning (RL) agents outperform humans on an increasing number of tasks, training them requires data equivalent to decades of human gameplay. Recent hierarchical RL methods have increased sample efficiency by…
We introduce NoisyNet, a deep reinforcement learning agent with parametric noise added to its weights, and show that the induced stochasticity of the agent's policy can be used to aid efficient exploration. The parameters of the noise are…
In online reinforcement learning (RL), efficient exploration remains particularly challenging in high-dimensional environments with sparse rewards. In low-dimensional environments, where tabular parameterization is possible, count-based…
All reinforcement learning algorithms must handle the trade-off between exploration and exploitation. Many state-of-the-art deep reinforcement learning methods use noise in the action selection, such as Gaussian noise in policy gradient…
Exploration is essential for reinforcement learning (RL). To face the challenges of exploration, we consider a reward-free RL framework that completely separates exploration from exploitation and brings new challenges for exploration…
Deep learning algorithms have been shown to perform extremely well on many classical machine learning problems. However, recent studies have shown that deep learning, like other machine learning techniques, is vulnerable to adversarial…
We study reinforcement learning (RL) for decision processes with non-Markovian reward, in which high-level knowledge of the task in the form of reward machines is available to the learner. We consider probabilistic reward machines with…
This paper presents a general framework for exploiting the representational capacity of neural networks to approximate complex, nonlinear reward functions in the context of solving the inverse reinforcement learning (IRL) problem. We show…
Posterior sampling for reinforcement learning (PSRL) is an effective method for balancing exploration and exploitation in reinforcement learning. Randomised value functions (RVF) can be viewed as a promising approach to scaling PSRL.…
Deep reinforcement learning has been successfully applied to several visual-input tasks using model-free methods. In this paper, we propose a model-based approach that combines learning a DNN-based transition model with Monte Carlo tree…
A promising technique for exploration is to maximize the entropy of visited state distribution, i.e., state entropy, by encouraging uniform coverage of visited state space. While it has been effective for an unsupervised setup, it tends to…
The recent success of denoising diffusion models has significantly advanced text-to-image generation. While these large-scale pretrained models show excellent performance in general image synthesis, downstream objectives often require…
Recent analyses question whether reinforcement learning (RL) is responsible for strong reasoning in large language models (LLMs). At the same time, distillation and inference-time sampling, including power sampling, have emerged as…
Reinforcement learning (RL) agents improve through trial-and-error, but when reward is sparse and the agent cannot discover successful action sequences, learning stagnates. This has been a notable problem in training deep RL agents to…
While deep reinforcement learning has achieved promising results in challenging decision-making tasks, the main bones of its success --- deep neural networks are mostly black-boxes. A feasible way to gain insight into a black-box model is…
Deep reinforcement learning has demonstrated superhuman performance in complex decision-making tasks, but it struggles with generalization and knowledge reuse - key aspects of true intelligence. This article introduces a novel approach that…