Analyzing the effect of stochastic transitions in policy gradients in deep reinforcement learning (2019)
- Authors:
- USP affiliated authors: BARROS, LELIANE NUNES DE - IME ; LOVATTO, ÂNGELO GREGÓRIO - IME ; BUENO, THIAGO PEREIRA - IME
- Unidade: IME
- DOI: 10.1109/BRACIS.2019.00079
- Subjects: APRENDIZADO COMPUTACIONAL; PROCESSOS ESTOCÁSTICOS
- Agências de fomento:
- Language: Inglês
- Imprenta:
- Publisher: IEEE
- Publisher place: Piscataway
- Date published: 2019
- Source:
- Título: Proceedings
- Conference titles: Brazilian Conference on Intelligent Systems (BRACIS)
- Este periódico é de assinatura
- Este artigo NÃO é de acesso aberto
- Cor do Acesso Aberto: closed
-
ABNT
LOVATTO, Ângelo Gregório e BUENO, Thiago Pereira e BARROS, Leliane Nunes de. Analyzing the effect of stochastic transitions in policy gradients in deep reinforcement learning. 2019, Anais.. Piscataway: IEEE, 2019. Disponível em: https://doi.org/10.1109/BRACIS.2019.00079. Acesso em: 02 jan. 2026. -
APA
Lovatto, Â. G., Bueno, T. P., & Barros, L. N. de. (2019). Analyzing the effect of stochastic transitions in policy gradients in deep reinforcement learning. In Proceedings. Piscataway: IEEE. doi:10.1109/BRACIS.2019.00079 -
NLM
Lovatto ÂG, Bueno TP, Barros LN de. Analyzing the effect of stochastic transitions in policy gradients in deep reinforcement learning [Internet]. Proceedings. 2019 ;[citado 2026 jan. 02 ] Available from: https://doi.org/10.1109/BRACIS.2019.00079 -
Vancouver
Lovatto ÂG, Bueno TP, Barros LN de. Analyzing the effect of stochastic transitions in policy gradients in deep reinforcement learning [Internet]. Proceedings. 2019 ;[citado 2026 jan. 02 ] Available from: https://doi.org/10.1109/BRACIS.2019.00079 - Gradient estimation in model-based reinforcement learning: a study on linear quadratic environments
- Decision-aware model learning for actor-critic methods: when theory does not meet practice
- Exploration versus exploitation in model-based reinforcement learning: an empirical study
- Deep reactive policies for planning in stochastic nonlinear domains
- Planning in stochastic computation graphs: solving stochastic nonlinear problems with backpropagation
- Model-based policy gradients: an empirical study on linear quadratic environments
- On the performance of planning through backpropagation
- Real-time symbolic dynamic programming for hybrid MDPs
- A planner agent that tries its best in presence of nondeterminism
- Compilador de regras para geracao de um sistema especialista com encadeamento regressivo
Informações sobre o DOI: 10.1109/BRACIS.2019.00079 (Fonte: oaDOI API)
Download do texto completo
| Tipo | Nome | Link | |
|---|---|---|---|
 |
2980007.pdf |
How to cite
A citação é gerada automaticamente e pode não estar totalmente de acordo com as normas
