TreeQN and ATreeC: differentiable tree planning for deep reinforcement learning
Combining deep model-free reinforcement learning with on-line planning is a promising approach to building on the successes of deep RL. On-line planning with look-ahead trees has proven successful in environments where transition models are known a priori. However, in complex environments where tran...
Main Authors: | Farquhar, G, Rocktaeschel, T, Igl, M, Whiteson, S |
---|---|
Format: | Conference item |
Published: |
International Conference on Learning Representations
2018
|
Similar Items
-
Transient non−stationarity and generalisation in deep reinforcement learning
by: Igl, M, et al.
Published: (2021) -
Differentiable mapping of affine Qn and projective Pn spaces
by: M. A. Al-Khassani, et al.
Published: (2009-06-01) -
Differentiable mapping of affine Qn and projective Pn spaces
by: M. A. Al-Khassani, et al.
Published: (2009-06-01) -
Deep variational reinforcement learning for POMDPs
by: Igl, M, et al.
Published: (2018) -
Inductive biases and generalisation for deep reinforcement learning
by: Igl, M
Published: (2021)