Human-Level Control Through Deep Reinforcement Learning.

Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., et al. (2015). Human-Level Control Through Deep Reinforcement Learning. Nature, 518(7540), 529-533.

Type

Journal article

Intellectual base

Primary research

Year

2015

DOI

10.1038/nature14236

Link

https://doi.org/10.1038/nature14236

Cited from

biology_ecology, neuroscience, operations_research

Cited by

3 citations across 3 artifacts.

Each citation links to the sentence it supports in the citing article.

Primes

• Markov Decision Processes (MDPs)
  • (1988) TD methods, actor-critic architectures, and the broader Sutton-Barto book (1998, 2018) that crystallized the modern framework.

    This sourceIntroduced Deep Q-Networks (DQN) achieving human-level performance on Atari games via deep-neural-network function approximation in the MDP framework; landmark deep-RL result.

• Memory Consolidation
  • In machine learning, experience replay re-presents past transitions to stabilize what online updates would otherwise catastrophically forget, and continual-learning methods explicitly engineer a consolidation stage that protects past learning while incorporating new.

    This sourceIntroduces experience replay—storing and re-presenting transitions to stabilize learning against catastrophic interference, a direct port of hippocampal replay.

• Replay
  • In reinforcement learning, experience-replay buffers store transitions during interaction and resample them off-policy during training, the trick that made deep RL stable.

    This sourceIntroduces deep Q-learning with an experience-replay buffer that decorrelates transitions and stabilizes training.

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Registry ID ref:68e0f893cb3e · see in the full table