Abstract | ||
---|---|---|
Learned world models summarize an agent's experience to facilitate learning complex behaviors. While learning world models from high-dimensional sensory inputs is becoming feasible through deep learning, there are many potential ways for deriving behaviors from them. We present Dreamer, a reinforcement learning agent that solves long-horizon tasks from images purely by latent imagination. We efficiently learn behaviors by propagating analytic gradients of learned state values back through trajectories imagined in the compact state space of a learned world model. On 20 challenging visual control tasks, Dreamer exceeds existing approaches in data-efficiency, computation time, and final performance. |
Year | Venue | Keywords |
---|---|---|
2020 | ICLR | world model, latent dynamics, imagination, planning by backprop, policy optimization, planning, reinforcement learning, control, representations, latent variable model, visual control, value function |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
29 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hafner, Danijar | 1 | 0 | 1.69 |
Timothy P. Lillicrap | 2 | 4377 | 170.65 |
Lei Jimmy Ba | 3 | 8887 | 296.55 |
Mohammad Norouzi | 4 | 1212 | 56.60 |