An Accumulating Eligibility Trace is a type of eligibility trace where the trace increments in an accumulative way. For the memory vector $\textbf{e}_{t} \in \mathbb{R}^{b} \geq \textbf{0}$:
$$\mathbf{e_{0}} = \textbf{0}$$
$$\textbf{e}_{t} = \nabla{\hat{v}}\left(S_{t}, \mathbf{\theta}_{t}\right) + \gamma\lambda\textbf{e}_{t}$$
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Starcraft II | 7 | 28.00% |
Starcraft | 6 | 24.00% |
Reinforcement Learning (RL) | 4 | 16.00% |
Decision Making | 2 | 8.00% |
Language Modelling | 1 | 4.00% |
Large Language Model | 1 | 4.00% |
Offline RL | 1 | 4.00% |
Imitation Learning | 1 | 4.00% |
Image Forensics | 1 | 4.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |