Hello StackOverflow Community!
I have a question about Actor-Critic Models in Reinforcement Learning.
While listening policy gradient methods classes of Berkeley University, it is said in the lecture that in the actor-critic algorithms where we both optimize our policy with some policy parameters and our value functions with some value function parameters, we use same parameters in both optimization problems(i.e. policy parameters = value function parameters) in some algorithms (e.g. A2C/A3C)
I could not understand how this works. I was thinking that we should optimize them separately. How does this shared parameter solution helps us?
Thanks in advance :)
You can do it by sharing some (or all) layers of their network. If you do, however, you are assuming that there is a common state representation (the intermediate layer output) that is optimal w.r.t. both. This is a very strong assumption and it usually doesn't hold. It has been shown to work for learning from image, where you put (for instance) an autoencoder on the top both the actor and the critic network and train it using the sum of their loss function.
This is mentioned in PPO paper (just before Eq. (9)). However, they just say that they share layers only for learning Atari games, not for continuous control problems. They don't say why, but this can be explained as I said above: Atari games have a low-dimensional state representation that is optimal for both the actor and the critic (e.g., the encoded image learned by an autoencoder), while for continuous control you usually pass directly a low-dimensional state (coordinates, velocities, ...).
A3C, which you mentioned, was also used mostly for games (Doom, I think).
From my experience, in control sharing layers never worked if the state is already compact.
I am learning about the approach employed in Reinforcement Learning for robotics and I came across the concept of Evolutionary Strategies. But I couldn't understand how RL and ES are different. Can anyone please explain?
To my understanding, I know of two main ones.
1) Reinforcement learning uses the concept of one agent, and the agent learns by interacting with the environment in different ways. In evolutionary algorithms, they usually start with many "agents" and only the "strong ones survive" (the agents with characteristics that yield the lowest loss).
2) Reinforcement learning agent(s) learns both positive and negative actions, but evolutionary algorithms only learns the optimal, and the negative or suboptimal solution information are discarded and lost.
Example
You want to build an algorithm to regulate the temperature in the room.
The room is 15 °C, and you want it to be 23 °C.
Using Reinforcement learning, the agent will try a bunch of different actions to increase and decrease the temperature. Eventually, it learns that increasing the temperature yields a good reward. But it also learns that reducing the temperature will yield a bad reward.
For evolutionary algorithms, it initiates with a bunch of random agents that all have a preprogrammed set of actions it is going to do. Then the agents that has the "increase temperature" action survives, and moves onto the next generation. Eventually, only agents that increase the temperature survive and are deemed the best solution. However, the algorithm does not know what happens if you decrease the temperature.
TL;DR: RL is usually one agent, trying different actions, and learning and remembering all info (positive or negative). EM uses many agents that guess many actions, only the agents that have the optimal actions survive. Basically a brute force way to solve a problem.
I think the biggest difference between Evolutionary Strategies and Reinforcement Learning is that ES is a global optimization technique while RL is a local optimization technique. So RL can converge to a local optima converging faster while ES converges slower to a global minima.
Evolution Strategies optimization happens on a population level. An evolution strategy algorithm in an iterative fashion (i) samples a batch of candidate solutions from the search space (ii) evaluates them and (iii) discards the ones with low fitness values. The sampling for a new iteration (or generation) happens around the mean of the best scoring candidate solutions from the previous iteration. Doing so enables evolution strategies to direct the search towards a promising location in the search space.
Reinforcement learning requires the problem to be formulated as a Markov Decision Process (MDP). An RL agent optimizes its behavior (or policy) by maximizing a cumulative reward signal received on a transition from one state to another. Since the problem is abstracted as an MDP learning can happen on a step or episode level. Learning per step (or N steps) is done via temporal-Difference learning (TD) and per episode is done via Monte Carlo methods. So far I am talking about learning via action-value functions (learning the values of actions). Another way of learning is by optimizing the parameters of a neural network representing the policy of the agent directly via gradient ascent. This approach is introduced in the REINFORCE algorithm and the general approach known as policy-based RL.
For a comprehensive comparison check out this paper https://arxiv.org/pdf/2110.01411.pdf
Is there any easy way to merge properties of PPO with an A3C method? A3C methods run a number of parrel actors and optimize the parameters. I am trying to merge PPO with A3C.
PPO has a built-in mechanism(surrogate clipping objective function) to prevent large gradient updates & generally outperforms A3C on most continuous control environments.
In order for PPO to enjoy the benefits of parallel computing like A3C, Distributed PPO(DPPO) is the way to go.
Check out the links below to find out more information about DPPO.
Pseudo code from the original DeepMind paper
Original DeepMind paper: Emergence of Locomotion Behaviours in Rich Environments
If you plan to implement your DPPO code in Python with Tensorflow, I will suggest you to try Ray for the part on distributed execution.
Is it possible to use openai's gym environments for multi-agent games? Specifically, I would like to model a card game with four players (agents). The player scoring a turn starts the next turn. How would I model the necessary coordination between the players (e.g. who's turn it is next)? Ultimately, I would like to use reinforcement learning on four agents that play against each other.
Yes, it is possible to use OpenAI gym environments for multi-agent games. Although in the OpenAI gym community there is no standardized interface for multi-agent environments, it is easy enough to build an OpenAI gym that supports this. For instance, in OpenAI's recent work on multi-agent particle environments they make a multi-agent environment that inherits from gym.Env which takes the following form:
class MultiAgentEnv(gym.Env):
def step(self, action_n):
obs_n = list()
reward_n = list()
done_n = list()
info_n = {'n': []}
# ...
return obs_n, reward_n, done_n, info_n
We can see that the step function takes a list of actions (one for each agent) and returns a list of observations, list of rewards, list of dones, while stepping the environment forwards. This interface is representative of Markov Game, in which all agents take actions at the same time and each observe their own subsequent observation, reward.
However, this kind of Markov Game interface may not be suitable for all multi-agent environments. In particular, turn-based games (such as card games) might be better cast as an alternating Markov Game, in which agents take turns (i.e. actions) one at a time. For this kind of environment, you may need to include which agent's turn it is in the representation of state, and your step function would then just take a single action, and return a single observation, reward and done.
There is a multi-agent deep deterministic policy gradient MADDPG approach has been implemented by OpenAI team.
This is the repo to get started.
https://github.com/openai/multiagent-particle-envs
What you are looking for is PettingZoo, it's a set of environment with multi agent setting and they have a specific class / synthax to handle multi agent environment.
It's an interesting library because you can also use it with ray / rllib to use already implemented algorithm like PPO / Q-learning. Like in this exemple.
Rllib also have an implementation for multiagents environments. But you will have to dig deeper in the documentation to understand it.
There is a specific multi-agent environment for reinforcement learning here. It supports any number of agents written in any programming language. An example game is already implemented which happens to be a card game.
I'm programming a software agent to control a robot player in a simulated game of soccer. Ultimately I hope to enter it in the RoboCup competition.
Amongst the various challenges involved in creating such an agent, the motion of it's body is one of the first I'm facing. The simulation I'm targeting uses a Nao robot body with 22 hinge to control. Six in each leg, four in each arm and two in the neck:
(source: sourceforge.net)
I have an interest in machine learning and believe there must be some techniques available to control this guy.
At any point in time, it is known:
The angle of all 22 hinges
The X,Y,Z output of an accelerometer located in the robot's chest
The X,Y,Z output of a gyroscope located in the robot's chest
The location of certain landmarks (corners, goals) via a camera in the robot's head
A vector for the force applied to the bottom of each foot, along with a vector giving the position of the force on the foot's sole
The types of tasks I'd like to achieve are:
Running in a straight line as fast as possible
Moving at a defined speed (that is, one function that handles fast and slow walking depending upon an additional input)
Walking backwards
Turning on the spot
Running along a simple curve
Stepping sideways
Jumping as high as possible and landing without falling over
Kicking a ball that's in front of your feet
Making 'subconscious' stabilising movements when subjected to unexpected forces (hit by ball or another player), ideally in tandem with one of the above
For each of these tasks I believe I could come up with a suitable fitness function, but not a set of training inputs with expected outputs. That is, any machine learning approach would need to offer unsupervised learning.
I've seen some examples in open-source projects of circular functions (sine waves) wired into each hinge's angle with differing amplitudes and phases. These seem to walk in straight lines ok, but they all look a bit clunky. It's not an approach that would work for all of the tasks I mention above though.
Some teams apparently use inverse kinematics, though I don't know much about that.
So, what approaches are there for robot biped locomotion/ambulation?
As an aside, I wrote and published a .NET library called TinMan that provides basic interaction with the soccer simulation server. It has a simple programming model for the sensors and actuators of the robot's 22 hinges.
You can read more about RoboCup's 3D Simulated Soccer League:
http://en.wikipedia.org/wiki/RoboCup_3D_Soccer_Simulation_League
http://simspark.sourceforge.net/wiki/index.php/Main_Page
http://code.google.com/p/tin-man/
There is a significant body of research literature on robot motion planning and robot locomotion.
General Robot Locomotion Control
For bipedal robots, there are at least two major approaches to robot design and control (whether the robot is simulated or physically real):
Zero Moment Point - a dynamics-based approach to locomotion stability and control.
Biologically-inspired locomotion - a control approach modeled after biological neural networks in mammals, insects, etc., that focuses on use of central pattern generators modified by other motor control programs/loops to control overall walking and maintain stability.
Motion Control for Bipedal Soccer Robot
There are really two aspects to handling the control issues for your simulated biped robot:
Basic walking and locomotion control
Task-oriented motion planning
The first part is just about handling the basic control issues for maintaining robot stability (assuming you are using some physics-based model with gravity), walking in a straight-line, turning, etc. The second part is focused on getting your robot to accomplish specific tasks as a soccer player, e.g., run toward the ball, kick the ball, block an opposing player, etc. It is probably easiest to solve these separately and link the second part as a higher-level controller that sends trajectory and goal directives to the first part.
There are a lot of relevant papers and books which could be suggested, but I've listed some potentially useful ones below that you may wish to include in whatever research you have already done.
Reading Suggestions
LaValle, Steven Michael (2006). Planning Algorithms, Cambridge University Press.
Raibert, Marc (1986). Legged Robots that Balance. MIT Press.
Vukobratovic, Miomir and Borovac, Branislav (2004). "Zero-Moment Point - Thirty Five Years of its Life", International Journal of Humanoid Robotics, Vol. 1, No. 1, pp 157–173.
Hirose, Masato and Takenaka, T (2001). "Development of the humanoid robot ASIMO", Honda R&D Technical Review, vol 13, no. 1.
Wu, QiDi and Liu, ChengJu and Zhang, JiaQi and Chen, QiJun (2009). "Survey of locomotion control of legged robots inspired by biological concept ", Science in China Series F: Information Sciences, vol 52, no. 10, pp 1715--1729, Springer.
Wahde, Mattias and Pettersson, Jimmy (2002) "A brief review of bipedal robotics research", Proceedings of the 8th Mechatronics Forum International Conference, pp 480-488.
Shan, J., Junshi, C. and Jiapin, C. (2000). "Design of central pattern generator for
humanoid robot walking based on multi-objective GA", In: Proc. of the IEEE/RSJ
International Conference on Intelligent Robots and Systems, pp. 1930–1935.
Chestnutt, J., Lau, M., Cheung, G., Kuffner, J., Hodgins, J., and Kanade, T. (2005). "Footstep planning for the Honda ASIMO humanoid", Proceedings of the 2005 IEEE International Conference on Robotics and Automation (ICRA 2005), pp 629-634.
I was working on a project not that dissimilar from this (making a robotic tuna) and one of the methods we were exploring was using a genetic algorithm to tune the performance of an artificial central pattern generator (in our case the pattern was a number of sine waves operating on each joint of the tail). It might be worth giving a shot, Genetic Algorithms are another one of those tools that can be incredibly powerful, if you are careful about selecting a fitness function.
Here's a great paper from 1999 by Peter Nordin and Mats G. Nordahl that outlines an evolutionary approach to controlling a humanoid robot, based on their experience building the ELVIS robot:
An Evolutionary Architecture for a Humanoid Robot
I've been thinking about this for quite some time now and I realized that you need at least two intelligent "agents" to make this work properly. The basic idea is that you have two types intelligent activity here:
Subconscious Motor Control (SMC).
Conscious Decision Making (CDM).
Training for the SMC could be done on-line... if you really think about it: defining success within motor control is basically done when you provide a signal to your robot, it evaluates that signal and either accepts it or rejects it. If your robot accepts a signal and it results in a "failure", then your robot goes "offline" and it can't accept any more signals. Defining "failure" and "offline" could be tricky, but I was thinking that it would be a failure if, for example, a sensor on the robot indicates that the robot is immobile (laying on the ground).
So your fitness function for the SMC might be something of the sort: numAcceptedSignals/numGivenSignals + numFailure
The CDM is another AI agent that generates signals and the fitness function for it could be: (numSignalsAccepted/numSignalsGenerated)/(numWinGoals/numLossGoals)
So what you do is you run the CDM and all the output that comes out of it goes to the SMC... at the end of a game you run your fitness functions. Alternately you can combine the SMC and the CDM into a single agent and you can make a composite fitness function based on the other two fitness functions. I don't know how else you could do it...
Finally, you have to determine what constitutes a learning session: is it half a game, full game, just a few moves, etc. If a game lasts 1 minute and you have a total of 8 players on the field, then the process of training could be VERY slow!
Update
Here is a quick reference to a paper that used genetic programming to create "softbots" that play soccer: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.36.136&rep=rep1&type=pdf
With regards to your comments: I was thinking that for the subconscious motor control (SMC), the signals would come from the conscious decision maker (CDM). This way you're evolving your SMC agent to properly handle the CDM agent's commands (signals). You want to maximize the up-time of the SMC agent regardless of what the CDM agent says.
The SMC agent receives an input, for example a vector force on a joint, and it then runs it through its processing unit to determine if it should execute that input or if it should reject it. The SMC should only execute inputs that it doesn't "think" it will recover from and it should reject inputs that it "thinks" would lead to a "catastrophic failure".
Now the SMC agent has an output: accept or reject a signal (1 or 0). The CDM can use that signal for its own training... the CDM wants to maximize the number of signals that the SMC accepts and it also wants to satisfy a goal: a high score for its own team and a low score for the opposing team. So the CDM has its own processing unit that is being evolved to satisfy both of those needs. Your reference provided a 3-layer design, while mine is only a 2-layer... I think mine was a right step in towards the 3-layer design.
One more thing to note here: is falling really a "catastrophic failure"? What if your robot falls, but the CDM makes it stand up again? I think that would be a valid behavior, so you shouldn't penalize the robot for falling... perhaps a better thing to do is penalize it for the amount of time it takes in order to perform a goal (not necessarily a soccer goal).
There is this tutorial on humanoid locomotion control that describes the software stack used on the HRP-4 humanoid (which can walk or climb stairs). It consists mainly of:
Linear inverted pendulum: a simplified model for balancing. It involves only the center of mass (COM) and ZMP already mentioned in other answers.
Trajectory optimization: the robot computes what it wants to do, ideally, for the next 2 seconds or so. It keeps recomputing this trajectory as it moves, which is known as model predictive control.
Balance control: the last stage that corrects the robot's posture based on sensor measurements and the desired trajectory.
Follow links to the academic papers and source code to learn more.