BYOL-Explore: Exploration by Bootstrapped Prediction
We present BYOL-Explore, a conceptually simple yet general approach for curiosity-driven exploration in visually-complex environments. BYOL-Explore learns a world representation, the world dynamics, and an exploration policy all-together by optimizing a single prediction loss in the latent space with no additional auxiliary objective. We show that BYOL-Explore is effective in DM-HARD-8, a challenging partially-observable continuous-action hard-exploration benchmark with visually-rich 3-D environments. On this benchmark, we solve the majority of the tasks purely through augmenting the extrinsic reward with BYOL-Explore s intrinsic reward, whereas prior work could only get off the ground with human demonstrations. As further evidence of the generality of BYOL-Explore, we show that it achieves superhuman performance on the ten hardest exploration games in Atari while having a much simpler design than other competitive agents.
Code (0)
등록된 구현이 없습니다.
Tasks
PredictionSimilar Papers 제목 키워드 기반
Deep Exploration via Bootstrapped DQN
Efficient exploration in complex environments remains a major challenge for reinforcement learning. We propose bootstrapped DQN, a simple algorithm that explores in a computationally and statistically efficient manner th…
Atari GamesEfficient Explorationreinforcement-learningReinforcement Learning+1Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments
Consider the problem of exploration in sparse-reward or reward-free environments, such as in Montezuma's Revenge. In the curiosity-driven paradigm, the agent is rewarded for how much each realized outcome differs from th…
Atari GamesMontezuma's RevengeOptimistic Exploration with Backward Bootstrapped Bonus for Deep Reinforcement Learning
Optimism in the face of uncertainty is a principled approach for provably efficient exploration for reinforcement learning in tabular and linear settings. However, such an approach is challenging in developing practical …
Atari GamesDeep Reinforcement LearningEfficient ExplorationQ-Learning+3Adversarial network embedding with bootstrapped representations for sparse networks
The inherent sparsity of real-world networks presents challenges in learning-rich embeddings and accurately reconstructing networks. To address these challenges, a novel method termed Adversarial Network Embedding with B…
Data VisualizationLink PredictionNetwork EmbeddingNode ClassificationBootstrapped Representation Learning on Graphs
Current state-of-the-art self-supervised learning methods for graph neural networks are based on contrastive learning. As such, they heavily depend on the construction of augmentations and negative examples. Increasing t…
Contrastive LearningLinear evaluationRepresentation LearningSelf-Supervised Learning