The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Reinforcement Learning Using a Continuous Time Actor-Critic Framework with Spiking Neurons
Open accessAbstract
Animals repeat rewarded behaviors, but the physiological basis of reward-based learning has only been partially elucidated. On one hand, experimental evidence shows that the neuromodulator dopamine carries information about rewards and affects synaptic plasticity. On the other hand, the theory of reinforcement learning provides a framework for reward-based learning. Recent models of reward-modulated spike-timing-dependent plasticity have made first steps towards bridging the gap between the two approaches, but faced two problems. First, reinforcement learning is typically formulated in a discrete framework, ill-adapted to the description of natural situations. Second, biologically plausible models of reward-modulated spike-timing-dependent plasticity require precise calculation of the reward prediction error, yet it remains to be shown how this can be computed by neurons. Here we propose a solution to these problems by extending the continuous temporal difference (TD) learning of Doya (2000) to the case of spiking neurons in an actor-critic network operating in continuous time, and with continuous state and action representations. In our model, the critic learns to predict expected future rewards in real time. Its activity, together with actual rewards, conditions the delivery of a neuromodulatory TD signal to itself and to the actor, which is responsible for action choice. In simulations, we show that such an architecture can solve a Morris water-maze-like navigation task, in a number of trials consistent with reported animal performance. We also use our model to solve the acrobot and the cartpole problems, two complex motor control tasks. Our model provides a plausible way of computing reward prediction error in the brain. Moreover, the analytically derived learning rule is consistent with experimental evidence for dopamine-modulated spike-timing-dependent plasticity.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A neural substrate of prediction and reward
Schultz, W., Dayan, P., & Montague, P. R. (1997) · Science · doi:10.1126/science.275.5306.1593 · Cited by 9,388
Watkins, C. J. C. H., & Dayan, P. (1992) · Machine Learning · doi:10.1007/bf00992698 · Cited by 9,083
Learning to predict by the methods of temporal differences
Sutton, R. S. (1988) · Machine Learning · doi:10.1007/bf00115009 · Cited by 5,148
The Neural Basis of Decision Making
Gold, J. I., & Shadlen, M. N. (2007) · Annual Review of Neuroscience · doi:10.1146/annurev.neuro.29.051605.113038 · Cited by 3,764
Synaptic tagging and long-term potentiation
Frey, U., & Morris, R. G. M. (1997) · Nature · doi:10.1038/385533a0 · Cited by 1,736 · cited 1×
“Direct experimental evidence of eligibility traces still lacks, but they are reminiscent of the synaptic tagging mechanism [57].”
BackgroundNeuron-type-specific signals for reward and punishment in the ventral tegmental area
Cohen, J. Y., Haesler, S., Vong, L., Lowell, B. B., & Uchida, N. (2012) · Nature · doi:10.1038/nature10754 · Cited by 1,318
A cellular mechanism of reward-related learning
Reynolds, J. N. J., Hyland, B. I., & Wickens, J. R. (2001) · Nature · doi:10.1038/35092560 · Cited by 879
Actor–critic models of the basal ganglia: new anatomical and computational perspectives
Joel, D., Niv, Y., & Ruppin, E. (2002) · Neural Networks · doi:10.1016/s0893-6080(02)00047-3 · Cited by 500
Neuromodulators control the polarity of spike-timing-dependent synaptic plasticity
Seol, G. H., Ziburkus, J., Huang, S., Song, L., Kim, I. T., Takamiya, K., Huganir, R. L., Lee, H.-K., & Kirkwood, A. (2007) · Neuron · doi:10.1016/j.neuron.2007.08.013 · Cited by 429
Differential regulation of fronto-executive function by the monoamines and acetylcholine
Robbins, T., & Roberts, A. (2007) · Cerebral Cortex · doi:10.1093/cercor/bhm066 · Cited by 279
Cited by
Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks
Fang, W., Yu, Z., Chen, Y., Masquelier, T., Huang, T., & Tian, Y. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00266 · Cited by 605
Neuromodulated Spike-Timing-Dependent Plasticity, and Theory of Three-Factor Learning Rules
Frémaux, N., & Gerstner, W. (2016) · Frontiers in Neural Circuits · doi:10.3389/fncir.2015.00085 · Cited by 413
Self-citationGerstner, W., Lehmann, M., Liakoni, V., Corneil, D., & Brea, J. (2018) · Frontiers in Neural Circuits · doi:10.3389/fncir.2018.00053 · Cited by 290
Self-citationThinking While Moving: Deep Reinforcement Learning with Concurrent Control
Xiao, T., Jang, E., Kalashnikov, D., Levine, S., Ibarz, J., Hausman, K., & Herzog, A. (2020) · arXiv · doi:10.48550/arxiv.2004.06089 · Cited by 25
A probabilistic successor representation for context-dependent learning
Geerts, J. P., Gershman, S. J., Burgess, N., & Stachenfeld, K. L. (2024) · Psychological Review · doi:10.1037/rev0000414 · Cited by 14
Metadata
- Authors
- Frémaux, N., Sprekeler, H., & Gerstner, W.
- Venue
- PLoS Computational Biology
- Publisher
- Public Library of Science (PLoS)
- Published
- 2013-04-11
- Volume
- 9
- Issue
- 4
- Pages
- e1003024
- ISSN
- 1553-734X (ISSN-L)
- 1553-7358
- OpenAlex
- W2020539709
- Cited by
- 209
- References
- 10
- FWCI
- 14.72
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.