Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Chung, Stephen"'
We propose the Thinker algorithm, a novel approach that enables reinforcement learning agents to autonomously interact with and utilize a learned world model. The Thinker algorithm wraps the environment with a world model and introduces new actions d
Externí odkaz:
http://arxiv.org/abs/2307.14993
Autor:
Chung, Stephen
A biologically plausible method for training an Artificial Neural Network (ANN) involves treating each unit as a stochastic Reinforcement Learning (RL) agent, thereby considering the network as a team of agents. Consequently, all units can learn via
Externí odkaz:
http://arxiv.org/abs/2307.13270
Autor:
Chung, Stephen
A biologically plausible method for training an Artificial Neural Network (ANN) involves treating each unit as a stochastic Reinforcement Learning (RL) agent, thereby considering the network as a team of agents. Consequently, all units can learn via
Externí odkaz:
http://arxiv.org/abs/2307.13256
Autor:
Clark, Alan, Siddiqui, Shoaib Ahmed, Kirk, Robert, Anwar, Usman, Chung, Stephen, Krueger, David
Existing offline reinforcement learning (RL) algorithms typically assume that training data is either: 1) generated by a known policy, or 2) of entirely unknown origin. We consider multi-demonstrator offline RL, a middle ground where we know which de
Externí odkaz:
http://arxiv.org/abs/2211.14827
Autor:
Chung, Stephen
An artificial neural network can be trained by uniformly broadcasting a reward signal to units that implement a REINFORCE learning rule. Though this presents a biologically plausible alternative to backpropagation in training a network, the high vari
Externí odkaz:
http://arxiv.org/abs/2010.09770
Autor:
Chung, Stephen
Nearly all state-of-the-art deep learning algorithms rely on error backpropagation, which is generally regarded as biologically implausible. An alternative way of training an artificial neural network is through treating each unit in the network as a
Externí odkaz:
http://arxiv.org/abs/2010.07893
Autor:
Chung, Stephen, Kozma, Robert
Spiking neuron networks have been used successfully to solve simple reinforcement learning tasks with continuous action set applying learning rules based on spike-timing-dependent plasticity (STDP). However, most of these models cannot be applied to
Externí odkaz:
http://arxiv.org/abs/2008.13044
Autor:
Chung, Stephen
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:6384-6393
An artificial neural network can be trained by uniformly broadcasting a reward signal to units that implement a REINFORCE learning rule. Though this presents a biologically plausible alternative to backpropagation in training a network, the high vari