Subscribe to RL Weekly

Get the highlights of reinforcement learning in both research and industry every week.

Emergent Tool Use from Multi-Agent Autocurricula

Bowen Baker1*, Ingmar Kanitscheider1*, Todor Markov1*, Yi Wu1*, Glenn Powell1*, Bob McGrew1*, Igor Mordatch2*,

1OpenAI, 2Google Brain

What it says

Consider a simulated environment of a two-team hide-an-seek game, where the hiders (blue) are tasked to avoid being seen by the seekers, whereas the seekers (red) are tasked to keep vision of the hiders. What makes the problem interesting is the fact that their are obstacles and objects in the environment that the hiders and seekers can use. Also, the hiders are given a “preparation phase” where they can change the environment to their advantage while the seekers are immobilized. Changing the environment can be done in two ways: moving the objects around and locking objects in place. The reward scheme is simple: if all hiders are hidden from the seekers, the hiders get +1 reward and the seekers get -1 reward. If at least 1 hider is visible to the seekers, the seekers get +1 reward and the hiders get -1 reward.

In this simple environment, complex behavior emerge as the episode progresses. At first, the hiders simply hide from the seekers without using the objects. Then, they start using obstacles and objects during the preparation phase to create a “shelter.” When the seekers learn to breach this shelter using the ramp object, the hiders then learn to bring the ramp into the shelter or lock the ramps far away from the shelter so that the seekers cannot use them. The seekers then learn to “box surf,” moving on top of the box object, to breach the shelter, where the hiders react by locking all objects during the preparation phase.

Agents are trained using self-play, and the agent policies are trained with Proximal Policy Optimization (PPO). “All agents share the same policy parameters but act and observe independently.” The training is distributed using the rapid framework, and needs 132.3 million episodes (31.7 billion frames) over 34 hours of training to reach the “final stage” of observed agent behaviors.

I recommend those who are interested to start by watching the short YouTube Video above, then reading the post in the OpenAI website.

Read more

Attraction-Repulsion Actor Critic for Continuous Control Reinforcement Learning (ARAC)

Thang Doan12*, Bogdan Mazoure12*, Audrey Durand23, Joelle Pineau124, R Devon Hjel256,

1McGill University, 2Mila, 3Université Laval, 4Facebook AI Research, 5MSR Montreal, 6Université de Montréal

What it says

Large action spaces are problematic for reinforcement learning, as they can lead to local optimas in dense-reward environments. In these environments, exploration is necessary during training to better cover the action space. The authors propose a new population-based exploration method, where a population of agents cover different parts of the action space. In other words, we want agents that can imitate a target policy using a different path.

Through the Attraction-Repulsion (AR) auxiliary loss shown above, the population of agents are encouraged to attract or repel one another. The AR loss measures the KL-divergence of two policies. If the coefficient in front of the KL divergence is positive, the agents “repel”, and if it is negative, the agents “attract” one another. To calculate the AR loss of a policy, the algorithm keeps a fixed-size policy archive (Section 3.1).

The training of Attraction-Repulsion Actor-Critic (ARAC) is a repetition of sample collection, critic updates, actor updates, and actor evaluation. To update the critic network, ARAC identifies top-K best agent (“elites”) and only uses these policies. Also, when updating the actor networks, only the top-K agents use the AR loss (Appendix 6.1).

In MuJoCo benchmarks, ARAC is shown to outperform CEM-TD3, CERL, ERL, SAC-NF, SAC, and TD3 in most tasks.

As a sidenote, the paper mentions the Machine Learning Reproducibility Checklist in its appendix and points out how the paper satisfies each point.

Read more

External resources

Making Efficient Use of Demonstrations to Solve Hard Exploration Problems

Tom Le Paine1*, Caglar Gulcehre1*, Bobak Shahriari1, Misha Denil1, Matt Hoffman1, Hubert Soyer1, Richard Tanburn1, Steven Kapturowski1, Neil Rabinowitz1, Duncan Williams1, Gabriel Barth-Maron1, Ziyu Wang1, Nando de Freitas1, Worlds Team1,

1DeepMind, London

What it says

Learning from demonstrations is very effective in many hard exploration environments (such as Montezuma’s Revenge) and helps reducing sample efficiency. However, it is challenging to use demonstrations if there is a wide variety of possible initial conditions, since the learner must generalize between these different environment configurations.

To solve these types of problems, the authors propose a new algorithm: Recurrent Replay Distributed DQN from Demonstrations (R2D3). As the name suggests, the system is similar to that of Recurrent Replay Distributed DQN (R2D2) and Deep Q-Learning from Demonstrations (DQfD). As in R2D2, there are multiple recurrence actor processes that run independently, adding transitions to the shared experience replay buffer. To incorporate demonstrations like DQfD, there is another replay buffer, the demo replay buffer, where expert demonstrations are stored. Using a “demo-ratio” hyperparameter, the agent uses experience from both replay buffers.

R2D3 is tested on the “Hard-Eight test suite” (Appendix B.1) with three baseline algorithm: Behavior Cloning, R2D2, and DQfD. R2D3 is the only algorithm that solves any of the tasks, showing that aspects from both R2D2 and DQfD are needed to succeed in these environments. The authors also find that the algorithm in sensitive to the “demo-ratio” hyperparameter and that the lower demo-ratios consistently outperform higher demo-ratios (Section 6.2, Figure 6).

Read more

External resources

Here are some more exciting news in RL since the last issue:

Thank you for reading RL Weekly. Please feel free to leave any feedback!