Search on the Replay Buffer: Bridging Planning and Reinforcement Learning
June 12, 2019 Β· Declared Dead Β· π Neural Information Processing Systems
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine
arXiv ID
1906.05253
Category
cs.AI: Artificial Intelligence
Cross-listed
cs.LG,
cs.RO
Citations
334
Venue
Neural Information Processing Systems
Last Checked
1 month ago
Abstract
The history of learning for control has been an exciting back and forth between two broad classes of algorithms: planning and reinforcement learning. Planning algorithms effectively reason over long horizons, but assume access to a local policy and distance metric over collision-free paths. Reinforcement learning excels at learning policies and the relative values of states, but fails to plan over long horizons. Despite the successes of each method in various domains, tasks that require reasoning over long horizons with limited feedback and high-dimensional observations remain exceedingly challenging for both planning and reinforcement learning algorithms. Frustratingly, these sorts of tasks are potentially the most useful, as they are simple to design (a human only need to provide an example goal state) and avoid reward shaping, which can bias the agent towards finding a sub-optimal solution. We introduce a general control algorithm that combines the strengths of planning and reinforcement learning to effectively solve these tasks. Our aim is to decompose the task of reaching a distant goal state into a sequence of easier tasks, each of which corresponds to reaching a subgoal. Planning algorithms can automatically find these waypoints, but only if provided with suitable abstractions of the environment -- namely, a graph consisting of nodes and edges. Our main insight is that this graph can be constructed via reinforcement learning, where a goal-conditioned value function provides edge weights, and nodes are taken to be previously seen observations in a replay buffer. Using graph search over our replay buffer, we can automatically generate this sequence of subgoals, even in image-based environments. Our algorithm, search on the replay buffer (SoRB), enables agents to solve sparse reward tasks over one hundred steps, and generalizes substantially better than standard RL algorithms.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Artificial Intelligence
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI
R.I.P.
π»
Ghosted
Addressing Function Approximation Error in Actor-Critic Methods
R.I.P.
π»
Ghosted
Explanation in Artificial Intelligence: Insights from the Social Sciences
R.I.P.
π»
Ghosted
Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
R.I.P.
π»
Ghosted
Complex Embeddings for Simple Link Prediction
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Language Models are Few-Shot Learners
R.I.P.
π»
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
π»
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
π»
Ghosted