1 code implementation • NeurIPS 2023 • Stephen Chung, Ivan Anokhin, David Krueger
This approach eliminates the need for handcrafted planning algorithms by enabling the agent to learn how to plan autonomously and allows for easy interpretation of the agent's plan with visualization.
no code implementations • 25 Jul 2023 • Stephen Chung
Notably, to our knowledge, this is the first learning rule for a network of Bernoulli-logistic units that is unbiased and scales well with the number of network's units in terms of learning speed.
no code implementations • 25 Jul 2023 • Stephen Chung
The first category includes algorithms that enable coordinated exploration among units, such as MAP propagation.
no code implementations • 27 Nov 2022 • Alan Clark, Shoaib Ahmed Siddiqui, Robert Kirk, Usman Anwar, Stephen Chung, David Krueger
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.
no code implementations • NeurIPS 2021 • Stephen Chung, Hava Siegelmann
Previous works have proved that recurrent neural networks (RNNs) are Turing-complete.
1 code implementation • 19 Oct 2020 • Stephen Chung
The high variance arises from the inefficient structural credit assignment since a single reward signal is used to evaluate the collective action of all units.
1 code implementation • NeurIPS 2021 • Stephen Chung
An alternative way of training an artificial neural network is through treating each unit in the network as a reinforcement learning agent, and thus the network is considered as a team of agents.
no code implementations • 29 Aug 2020 • Stephen Chung, Robert Kozma
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).