“Agent57: Outperforming the Human Atari Benchmark”, Adrià Puigdomènech, Bilal Piot, Steven Kapturowski, Pablo Sprechmann, Alex Vitvitskyi, Daniel Guo, Charles Blundell2020-03-31 (RNN, RL exploration, MuZero, RL scaling; backlinks; similar)⁠:

The Atari57 suite of games is a long-standing benchmark to gauge agent performance across a wide range of tasks. We’ve developed Agent57, the first deep reinforcement learning agent to obtain a score that is above the human baseline on all 57 Atari 2600 games. Agent57 combines an algorithm for efficient exploration with a meta-controller that adapts the exploration and long vs. short-term behavior of the agent.

…In 2012, the Arcade Learning environment—a suite of 57 Atari 2600 games (dubbed Atari57)—was proposed as a benchmark set of tasks: these canonical Atari games pose a broad range of challenges for an agent to master…Unfortunately, the average performance can fail to capture how many tasks an agent is doing well on, and so is not a good statistic for determining how general an agent is: it captures that an agent is doing sufficiently well, but not that it is doing sufficiently well on a sufficiently wide set of tasks. So although average scores have increased, until now, the number of above human games has not.

…Back in 2012, DeepMind developed the Deep Q-network agent (DQN) to tackle the Atari57 suite. Since then, the research community has developed many extensions and alternatives to DQN. Despite these advancements, however, all deep reinforcement learning agents have consistently failed to score in four games: Montezuma’s Revenge, Pitfall, Solaris and Skiing. For Agent57 to tackle these four challenging games in addition to the other Atari57 games, several changes to DQN were necessary.

• DQN improvements

  • Distributed agents

  • Short-term memory

  • Episodic memory

• Intrinsic motivation methods to encourage directed exploration

  • Seeking novelty over long time scales

  • Seeking novelty over short time scales

  • Meta-controller: learning to balance exploration with exploitation

• Agent57: putting it all together

…With Agent57, we have succeeded in building a more generally intelligent agent that has above-human performance on all tasks in the Atari57 benchmark. It builds on our previous agent Never Give Up, and instantiates an adaptive meta-controller that helps the agent to know when to explore and when to exploit, as well as what time-horizon it would be useful to learn with. A wide range of tasks will naturally require different choices of both of these trade-offs, therefore the meta-controller provides a way to dynamically adapt such choices.

Agent57 was able to scale with increasing amounts of computation: the longer it trained, the higher its score got. While this enabled Agent57 to achieve strong general performance, it takes a lot of computation and time; the data efficiency can certainly be improved. Additionally, this agent shows better 5^th percentile performance on the set of Atari57 games. This by no means marks the end of Atari research, not only in terms of data efficiency, but also in terms of general performance. We offer two views on this: firstly, analyzing the performance among percentiles gives us new insights on how general algorithms are. While Agent57 achieves strong results on the first percentiles of the 57 games and holds better mean and median performance than NGU or R2D2, as illustrated by MuZero, it could still obtain a higher average performance. Secondly, all current algorithms are far from achieving optimal performance in some games. To that end, key improvements to use might be enhancements in the representations that Agent57 uses for exploration, planning, and credit assignment.

Backlinks:

Similar Links: