Reinforcement studying (RL) algorithms can study abilities to unravel decision-making duties like taking part in video games, enabling robots to choose up objects, and even optimizing microchip designs. Nevertheless, working RL algorithms in the true world requires costly lively information assortment. Pre-training on numerous datasets has confirmed to allow data-efficient fine-tuning for particular person downstream duties in pure language processing (NLP) and imaginative and prescient issues. In the identical manner that BERT or GPT-3 fashions present general-purpose initialization for NLP, massive RL–pre-trained fashions might present general-purpose initialization for decision-making. So, we ask the query: Can we allow comparable pre-training to speed up RL strategies and create a general-purpose “spine” for environment friendly RL throughout varied duties?
In “Offline Q-learning on Various Multi-Job Information Each Scales and Generalizes”, to be printed at ICLR 2023, we talk about how we scaled offline RL, which can be utilized to coach worth capabilities on beforehand collected static datasets, to supply such a normal pre-training technique. We exhibit that Scaled Q-Studying utilizing a various dataset is enough to study representations that facilitate speedy switch to novel duties and quick on-line studying on new variations of a activity, enhancing considerably over present illustration studying approaches and even Transformer-based strategies that use a lot bigger fashions.
 |
Scaled Q-learning: Multi-task pre-training with conservative Q-learning
To offer a general-purpose pre-training strategy, offline RL must be scalable, permitting us to pre-train on information throughout completely different duties and make the most of expressive neural community fashions to amass highly effective pre-trained backbones, specialised to particular person downstream duties. We based mostly our offline RL pre-training technique on conservative Q-learning (CQL), a easy offline RL technique that mixes commonplace Q-learning updates with a further regularizer that minimizes the worth of unseen actions. With discrete actions, the CQL regularizer is equal to an ordinary cross-entropy loss, which is a straightforward, one-line modification on commonplace deep Q-learning. A number of essential design selections made this doable:
- Neural community dimension: We discovered that multi-game Q-learning required massive neural community architectures. Whereas prior strategies usually used comparatively shallow convolutional networks, we discovered that fashions as massive as a ResNet 101 led to vital enhancements over smaller fashions.
- Neural community structure: To study pre-trained backbones which are helpful for brand new video games, our last structure makes use of a shared neural community spine, with separate 1-layer heads outputting Q-values of every sport. This design avoids interference between the video games throughout pre-training, whereas nonetheless offering sufficient information sharing to study a single shared illustration. Our shared imaginative and prescient spine additionally utilized a discovered place embedding (akin to Transformer fashions) to maintain monitor of spatial info within the sport.
- Representational regularization: Current work has noticed that Q-learning tends to endure from representational collapse points, the place even massive neural networks can fail to study efficient representations. To counteract this problem, we leverage our prior work to normalize the final layer options of the shared a part of the Q-network. Moreover, we utilized a categorical distributional RL loss for Q-learning, which is thought to supply richer representations that enhance downstream activity efficiency.
The multi-task Atari benchmark
We consider our strategy for scalable offline RL on a set of Atari video games, the place the objective is to coach a single RL agent to play a group of video games utilizing heterogeneous information from low-quality (i.e., suboptimal) gamers, after which use the ensuing community spine to rapidly study new variations in pre-training video games or utterly new video games. Coaching a single coverage that may play many alternative Atari video games is tough sufficient even with commonplace on-line deep RL strategies, as every sport requires a special technique and completely different representations. Within the offline setting, some prior works, comparable to multi-game determination transformers, proposed to dispense with RL solely, and as a substitute make the most of conditional imitation studying in an try to scale with massive neural community architectures, comparable to transformers. Nevertheless, on this work, we present that this type of multi-game pre-training will be executed successfully by way of RL by using CQL together with just a few cautious design selections, which we describe beneath.
Scalability on coaching video games
We consider the Scaled Q-Studying technique’s efficiency and scalability utilizing two information compositions: (1) close to optimum information, consisting of all of the coaching information showing in replay buffers of earlier RL runs, and (2) low high quality information, consisting of information from the primary 20% of the trials within the replay buffer (i.e., solely information from extremely suboptimal insurance policies). In our outcomes beneath, we examine Scaled Q-Studying with an 80-million parameter mannequin to multi-game determination transformers (DT) with both 40-million or 80-million parameter fashions, and a behavioral cloning (imitation studying) baseline (BC). We observe that Scaled Q-Studying is the one strategy that improves over the offline information, attaining about 80% of human normalized efficiency.
 |
Additional, as proven beneath, Scaled Q-Studying improves by way of efficiency, nevertheless it additionally enjoys favorable scaling properties: simply as how the efficiency of pre-trained language and imaginative and prescient fashions improves as community sizes get larger, having fun with what is usually referred as “power-law scaling”, we present that the efficiency of Scaled Q-learning enjoys comparable scaling properties. Whereas this can be unsurprising, this type of scaling has been elusive in RL, with efficiency usually deteriorating with bigger mannequin sizes. This means that Scaled Q-Studying together with the above design selections higher unlocks the flexibility of offline RL to make the most of massive fashions.
 |
High-quality-tuning to new video games and variations
To guage fine-tuning from this offline initialization, we think about two settings: (1) fine-tuning to a brand new, solely unseen sport with a small quantity of offline information from that sport, equivalent to 2M transitions of gameplay, and (2) fine-tuning to a brand new variant of the video games with on-line interplay. The fine-tuning from offline gameplay information is illustrated beneath. Be aware that this situation is mostly extra favorable to imitation-style strategies, Determination Transformer and behavioral cloning, because the offline information for the brand new video games is of comparatively high-quality. Nonetheless, we see that most often Scaled Q-learning improves over various approaches (80% on common), in addition to devoted illustration studying strategies, comparable to MAE or CPC, which solely use the offline information to study visible representations slightly than worth capabilities.
 |
Within the on-line setting, we see even bigger enhancements from pre-training with Scaled Q-learning. On this case, illustration studying strategies like MAE yield minimal enchancment throughout on-line RL, whereas Scaled Q-Studying can efficiently combine prior information in regards to the pre-training video games to considerably enhance the ultimate rating after 20k on-line interplay steps.
These outcomes exhibit that pre-training generalist worth operate backbones with multi-task offline RL can considerably enhance efficiency of RL on downstream duties, each in offline and on-line mode. Be aware that these fine-tuning duties are fairly tough: the assorted Atari video games, and even variants of the identical sport, differ considerably in look and dynamics. For instance, the goal blocks in Breakout disappear within the variation of the sport as proven beneath, making management tough. Nevertheless, the success of Scaled Q-learning, notably as in comparison with visible illustration studying methods, comparable to MAE and CPC, means that the mannequin is in reality studying some illustration of the sport dynamics, slightly than merely offering higher visible options.
 |
| High-quality-tuning with on-line RL for variants of the sport Freeway, Hero, and Breakout. The brand new variant utilized in fine-tuning is proven within the backside row of every determine, the unique sport seen in pre-training is within the high row. High-quality-tuning from Scaled Q-Studying considerably outperforms MAE (a visible illustration studying technique) and studying from scratch with single-game DQN. |
Conclusion and takeaways
We introduced Scaled Q-Studying, a pre-training technique for scaled offline RL that builds on the CQL algorithm, and demonstrated the way it allows environment friendly offline RL for multi-task coaching. This work made preliminary progress in the direction of enabling extra sensible real-world coaching of RL brokers as an alternative choice to expensive and sophisticated simulation-based pipelines or large-scale experiments. Maybe in the long term, comparable work will result in usually succesful pre-trained RL brokers that develop broadly relevant exploration and interplay abilities from large-scale offline pre-training. Validating these outcomes on a broader vary of extra lifelike duties, in domains comparable to robotics (see some preliminary outcomes) and NLP, is a vital path for future analysis. Offline RL pre-training has a whole lot of potential, and we count on that we are going to see many advances on this space in future work.
Acknowledgements
This work was executed by Aviral Kumar, Rishabh Agarwal, Xinyang Geng, George Tucker, and Sergey Levine. Particular because of Sherry Yang, Ofir Nachum, and Kuang-Huei Lee for assist with the multi-game determination transformer codebase for analysis and the multi-game Atari benchmark, and Tom Small for illustrations and animation.
