Exploration in deep reinforcement learning: A survey
This paper reviews exploration techniques in deep reinforcement learning. Exploration
techniques are of primary importance when solving sparse reward problems. In sparse …
techniques are of primary importance when solving sparse reward problems. In sparse …
Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges
Continual learning (CL) is a particular machine learning paradigm where the data
distribution and learning objective change through time, or where all the training data and …
distribution and learning objective change through time, or where all the training data and …
Guiding pretraining in reinforcement learning with large language models
Reinforcement learning algorithms typically struggle in the absence of a dense, well-shaped
reward function. Intrinsically motivated exploration methods address this limitation by …
reward function. Intrinsically motivated exploration methods address this limitation by …
Off-policy deep reinforcement learning without exploration
Many practical applications of reinforcement learning constrain agents to learn from a fixed
batch of data which has already been gathered, without offering further possibility for data …
batch of data which has already been gathered, without offering further possibility for data …
Go-explore: a new approach for hard-exploration problems
A grand challenge in reinforcement learning is intelligent exploration, especially when
rewards are sparse or deceptive. Two Atari games serve as benchmarks for such hard …
rewards are sparse or deceptive. Two Atari games serve as benchmarks for such hard …
Cooperative exploration for multi-agent deep reinforcement learning
Exploration is critical for good results in deep reinforcement learning and has attracted much
attention. However, existing multi-agent deep reinforcement learning algorithms still use …
attention. However, existing multi-agent deep reinforcement learning algorithms still use …
Skew-fit: State-covering self-supervised reinforcement learning
Autonomous agents that must exhibit flexible and broad capabilities will need to be
equipped with large repertoires of skills. Defining each skill with a manually-designed …
equipped with large repertoires of skills. Defining each skill with a manually-designed …
Reconciling novelty and complexity through a rational analysis of curiosity.
Curiosity is considered to be the essence of science and an integral component of cognition.
What prompts curiosity in a learner? Previous theoretical accounts of curiosity remain …
What prompts curiosity in a learner? Previous theoretical accounts of curiosity remain …
Evolution-guided policy gradient in reinforcement learning
Abstract Deep Reinforcement Learning (DRL) algorithms have been successfully applied to
a range of challenging control tasks. However, these methods typically suffer from three core …
a range of challenging control tasks. However, these methods typically suffer from three core …
Revisiting rainbow: Promoting more insightful and inclusive deep reinforcement learning research
Since the introduction of DQN, a vast majority of reinforcement learning research has
focused on reinforcement learning with deep neural networks as function approximators …
focused on reinforcement learning with deep neural networks as function approximators …