coach
coach copied to clipboard
IntelLabs
Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
Hey guys, I'm having trouble installing coach in another environment doing the same exact process I did in the same computer. I just create a brand new conda environment with...
Following the tutorial (below, first full tutorial on google searching "custom OpenAI Gym environment tutorial") to create a custom OpenAI Gym environment. The environment works (can be stepped through, reset)...
I'm trying to port an OpenAI Gym Environment and use coach for the learn on top. The tutorial currently reads (emphasis mine): ``` Adding an Environment Adding your custom environments...
I'm trying to use Coach for the first time, with a custom made environment in Gym. I have a simple preset: from rl_coach.agents.rainbow_dqn_agent import RainbowDQNAgentParameters from rl_coach.graph_managers.basic_rl_graph_manager import BasicRLGraphManager from...
Latest code raises the following error. Same code on 12.1 works properly. ``` Original stack trace for 'main_level/agent/main/online/network_0/behavior/behavior': File "C:\Anaconda3\lib\site-packages\rl_coach\graph_managers\graph_manager.py", line 148, in create_graph self.level_managers, self.environments = self._create_graph(task_parameters) File "C:\Anaconda3\lib\site-packages\rl_coach\graph_managers\basic_rl_graph_manager.py",...
This extension to DQN and other algorithms looks pretty interesting to smooth out the variance of the Q estimations. From the abstract: > Sample inefficiency is a long-lasting problem in...
Is it possible to instruct Coach to use special environment parameters for the evaluation episodes?
Could you guide me how to expand this awesome work to support conditional RL?
I was watching some strange behaviors when evaluating a trained environment. The environment is deterministic and has a 'death switch' whenever a certain amount of actions had happened, and I...
I have been playing with the agent and noticed that my Q values are clustered along the [10..20] then I setup vmin=10 and vmax=20 but if vmin is bigger than...