We bring reinforcement learning into the real world.
Our production-grade open source reinforcement learning library.
Deploy, train and serve TensorForce models.
Reinforcement learning in the real world is hard. Let us make the software part easy for you. We build enterprise-grade deep reinforcement learning software and services. Our goal is to provide fully portable computation graphs for reinforcement learning in any industrial context, be it robotics, autonomous vehicles, manufacturing, or finance.
TensorForce is an open source reinforcement learning library on top of TensorFlow focused on providing clear APIs, readability and modularisation to deploy reinforcement learning solutions both in research and practice.
from tensorforce.agents import PPOAgent # Create a Proximal Policy Optimization agent agent = PPOAgent( states_spec=dict(type='float', shape=(10,)), actions_spec=dict(type='int', num_actions=10), network_spec=[ dict(type='dense', size=64), dict(type='dense', size=64) ], batch_size=1000, step_optimizer=dict( type='adam', learning_rate=1e-4 ) ) # Get new data from somewhere, e.g. a client to a web app client = MyClient('http://127.0.0.1', 8080) # Poll new state from client state = client.get_state() # Get prediction from agent, execute action = agent.act(state) reward = client.execute(action) # Add experience, agent automatically updates model according to batch size agent.observe(reward=reward, terminal=False)
Register your interest for very (!) occasional updates on our progress: